kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-30 00:00:23 +00:00
Code Issues Packages Projects Releases Wiki Activity
7,697 Commits 609 Branches 6,697 Tags
b7697
Commit Graph

225 Commits

Author SHA1 Message Date
Aaron Teo 046d5fd44e llama: use host memory if device reports 0 memory (#18587) 2026-01-09 05:34:56 +08:00
Julius Tischbein 2038101bd9 llama : add use_direct_io flag for model loading (#18166) 
* Adding --direct-io flag for model loading

* Fixing read_raw() calls

* Fixing Windows read_raw_at

* Changing type off_t to size_t for windows and Renaming functions

* disable direct io when mmap is explicitly enabled

* Use read_raw_unsafe when upload_backend is available, not functional on some devices with Vulkan and SYCL

* Fallback to std::fread in case O_DIRECT fails due to bad address

* Windows: remove const keywords and unused functions

* Update src/llama-mmap.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: jtischbein <jtischbein@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2026-01-08 08:35:30 +02:00
Tarek Dakhran 73d284a250 model : add LFM2-ColBert-350M (#18607) 
* model : add LFM2-ColBert-350M

* llama_model_n_embd_out() - returns `hparams.n_embd_out` if set and fallbacks to `hparams.n_embd`
 2026-01-05 19:52:56 +01:00
Sigbjørn Skjæret eadc4184ca llama : refactor rope_freq_base/scale_swa conversion and init (#18553) 
* refactor rope_freq_base/scale_swa conversion and init

* safe defaults for unknowns

* update relevant models

* grammar

* add get_rope_freq_scale to modern-bert

* const

* const

* log swa info
 2026-01-05 09:14:04 +01:00
Daniel Bevenius d3dce4e0a5 sampling : add support for backend sampling (#17004) 
* sampling : add support for backend sampling

This commit adds support for performing sampling operations on the
backend (e.g. GPU) as part of the model computation graph.

The motivation for this feature is to enable sampling to be performed
directly on the backend as part of the computation graph being executed,
allowing for some or all of the sampling to be done on the backend.

For example, the backend sampler chain might select/sample a token
directly in which case only the sampled token needs to be transferred
from device memory to host memory.

It is also possible for the backend samplers to perform filtering of
the logits, or compute and filter the probability distribution, in
which case only the filtered logits or probabilites need to be
transferred back to system memory for further processing by CPU
samplers.

Currently the backend sampling works in a similar manner to how
pooling works, it is a function that is called by build_graph and the
sampler operations become part of the models computation graph.

* llama-cli : add backend sampler configuration

* server : add backend sampling options/configuration

* webui : add backend sampling options

* ggml : add initial cumsum implementation for CUDA

* sampling : enable all backend sampler tests

This commit enables all exisiting backend sampler tests in the
test-backend-sampler. Previously, some tests were disabled because
there were missing ggml operation implementations.

* graph : do not include llama-model.h

* sampling : always expose sampled_ids

This commit precomputes and caches the full-vocab token id list in
llama_context's constructor, so llama_get_backend_sampled_token_ids_ith
always returns a valid pointer.

The motivation for this is that this enables both common/sampling.cpp
and src/llama-sampling.cpp can simplify their logic.

Not all backends samplers that process logits need to set the
sampled_tokens_id as they may not change the order of the logits, for
example the temperature sampler only scales the logits but does not
change their order. Simliar the logit bias sampler only adds bias to
specific token ids but does not change the order of the logits. In
these cases there will not be a device to host copy of the sampled
token ids, and this is the use case where having this precomputed
list is useful.

* sampling : ensure at most one output token per seq

This commit adds a check in the batch allocator to ensure that when
backend sampling is enabled, at most one output token is specified per
sequence.

* CUDA: Optimize argsort for gpu-based token sampling

Argsort is used for top-k currently. WE optimize argsort by 2 things:

1. Use `DeviceRadixSort` for single-row/sequence to parallelize it
   across our SMs
2. Use `DeviceSegmentedSort` for multi-row/sequence as this is the
   correct entrypoint (the function chooses different execution paths,
   it contains `DeviceSegmentedRadixSort` as one of the paths and will
   choose the best one according to heuristics.
   https://nvidia.github.io/cccl/cub/api/structcub_1_1DeviceSegmentedSort.html#overview

Some perf numbers for a RTX PRO 6000:

On the kernel level, tested with
`GGML_CUDA_DISABLE_GRAPHS=1 ./test-backend-ops -o ARGSORT perf`
Before:
```
  ARGSORT(type=f32,ne=[65000,16,1,1],order=0):                  4130 runs -   359.24 us/run
  ARGSORT(type=f32,ne=[200000,1,1,1],order=0):                  8192 runs -   861.34 us/run
  ARGSORT(type=f32,ne=[200000,16,1,1],order=0):                 1343 runs -  1020.01 us/run
```

After:
```
  ARGSORT(type=f32,ne=[65000,16,1,1],order=0):                  4130 runs -   312.41 us/run
  ARGSORT(type=f32,ne=[200000,1,1,1],order=0):                 16384 runs -    63.48 us/run
  ARGSORT(type=f32,ne=[200000,16,1,1],order=0):                 1343 runs -   874.36 us/run
```

---
On the model level, tested with
`llama-cli -m gpt-oss-20b-mxfp4.gguf -n 200 -p "What is
the Capital of Sweden?" -no-cnv -fa 1 --backend-sampling`

Before:
```
llama_perf_sampler_print:    sampling time =       0.25 ms /   207 runs   (    0.00 ms per token, 824701.20 tokens per second)
llama_perf_context_print:        load time =   18215.58 ms
llama_perf_context_print: prompt eval time =      28.20 ms /     7 tokens (    4.03 ms per token,   248.19 tokens per second)
llama_perf_context_print:        eval time =     714.79 ms /   199 runs   (    3.59 ms per token,   278.40 tokens per second)
llama_perf_context_print:       total time =     857.62 ms /   206 tokens
```

After
```
llama_perf_sampler_print:    sampling time =       0.25 ms /   207 runs   (    0.00 ms per token, 828000.00 tokens per second)
llama_perf_context_print:        load time =   18366.92 ms
llama_perf_context_print: prompt eval time =      35.92 ms /     7 tokens (    5.13 ms per token,   194.87 tokens per second)
llama_perf_context_print:        eval time =     532.79 ms /   199 runs   (    2.68 ms per token,   373.50 tokens per second)
llama_perf_context_print:       total time =     683.65 ms /   206 tokens
```

* sampling : remove version from sampler chain

This commit removes the version field from the sampler chain and instead
used the sampler pointer itself for change detection.

* sampling : always populate logits for sampled probs

This commit updates common/sampler.cpp set_logits and
src/llama-sampling.cpp llama_sampler_sample to always populate the
logits field when backend sampled probabilities are available.

The motivation for this is that this ensure that CPU sampler always have
access to the logits values even when probabilites have been produced by
backend samplers.

* sampling : simplify backend sampling logic decode

This commit tries to simplify the backend sampling logic in
llama_context::decode.

* squash! sampling : simplify backend sampling logic decode

Fix condition to check if backend actually sampled tokens, not just that
backend samplers are available.

* common : fix regression caused by extra memory allocations during sampling

* squash! sampling : simplify backend sampling logic decode

The commit fixes a variable shadowing issue in the
`llama_context::decode` function which was introduced in a previous
refactoring.

* squash! common : fix regression caused by extra memory allocations during sampling

Apply the same changes to llama-sampling.cpp, llama_sampler_sample as
were applied in commit 38f408c25.

* sampling : introduce sampling_info struct

This commit introduces a sampling_info struct to encapsulate all
backend sampling related data within the llama_context class.

It also updates to use more descriptive names for sampled tokens and
candidates in the backend sampler ggml data structure.

* sampling : return early if backend sampling is disabled

* sampling : use pinned memory for backend sampling buffers

* common, tools : refactor model loading to support backend samplers

This commit refactors the model loading process in common/common.cpp
to enable backend sampler to be configure prior to the llama_context
creation.

The motivation for this change is that just being able to set/reset the
backend samplers after the llama_context has been created will cause a
resize to occur in llama_context::output_reserve which we want to avoid.

* sampling : add stride variable for clarity

* sampling: clarify candidate ids usage in comments

* sampling : fix copying both sampled tokens and logits/probs from backend

This commit fixes the issue where both sampled tokens and logits/probs
were not being copied correctly from the backend to the host when
multiple backend samplers were used.

A test for this scenario has also been added to ensure that both types
of data are copied correctly when different backend samplers are
employed.

* tests : cleanup test-backend-sampler.cpp

* common : remove build-info.cpp from commit [no ci]

This file was generated during the build process and should not be
included in previous commits.

* sampling : cleanup and clarify output_reserve

* sampling : remove redundant checks for stride and size [no ci]

* sampling : add debug log when backend sampler selects token

This commit adds a debug log statement in the llama_sampler_sample
to indicate when a backend sampler has selected a token for a given
index.

The modification helps in tracing the sampling process and understanding
the flow of control when backend samplers are used.

* examples : update batched to use backend sampling

This commit updates the batched example to demonstrate how to use
backend samplers.

* llama-cli : fix dangling reference to sampler config

* common : initialize backend samplers

* samplers : add missing cont

* sampling : add assertions for contiguous tensors in async copy functions

* examples : add info about hybrid sampling in batched [no ci]

* sampling : remove backend-dist option (wip)

This commit removes the `--backend-dist` option and instead uses the
configured --samplers chain to determine which samplers run on the
backend.

Backend sampling is still enabled using With `--backend_sampling`, and
the sampler chain, either explictly specified using `--samplers` or the
default, is automatically analyzed to determine which samplers can run
on the backend. The system finds the longest contiguous chain of
backend supported samplers from the start of the sampler sequence.
For example:

* If the chain is `top-k -> temperature -> top-p`, and both `top-k` and
  `temperature` are backend-supported but `top-p` is not, then `top-k`
  and `temperature` will run on the backend, while `top-p` and
  subsequent samplers run on the CPU.

* If all configured samplers are supported, the final distribution
  sampling will also happen on the backend, transferring only the
  sampled token IDs back to the host.

* If the sampler chain starts with an unsupported sampler (e.g.,
  `penalties`), all sampling runs on the CPU. Note that this is
  currently the case with the default sampler so to use backend sampling
  it is required to specify a sampler chain. See below for an example.

The following shows how llama-cli can be run with backend sampling:
```console
$ llama-cli -m models/Qwen2.5-VL-3B-Instruct-Q8_0.gguf \
    --prompt 'What is the capital of Sweden?' \
    -n 20 \
    -no-cnv \
    --verbose-prompt \
    -ngl 40 \
    --backend-sampling \
    --samplers 'top_k;temperature'
```
In this case the all sampling will happen on the backend since both
`top_k` and `temperature` are supported backend samplers.

To enable a partial backend sampling (hybrid sampling), for example
running `top_k` and `temperature` on the backend and `typ_p` on the CPU
the following sampler chain could be specified:
```console
$ llama-cli -m models/Qwen2.5-VL-3B-Instruct-Q8_0.gguf \
    --prompt 'What is the capital of Sweden?' \
    -n 20 \
    -no-cnv \
    --verbose-prompt \
    -ngl 40 \
    --backend-sampling \
    --samplers 'top_k;temperature;top_p'
```

If this looks good then I'll follow up with updates the llama-cli and
llama-server documentation to reflect these changes.

* CUDA: Add top-k implementation

* sampling : add min-p backend sampler

* Use `FetchContent` over CPM as it's bundled with CMake

Thanks @ggerganov for the suggestion

* common : add get_active_samplers function to check enabled samplers

This commit adds a function to check if a sampler is actually enabled,
meaning that it does not have values that disables its effect. This is
then used by the backend samplers initialization to avoid considering
samplers that are not enabled when determining the split point between
them.

The motivation for this is that this allows the default sampler chain
for `--samplers` to be used and any sampler that is not enabled will not
cause the backend samplers to be skipped.
For example, before this change if the penalties sampler was included in
the samplers list but had default values that disable it, it would cause
the backend samplers to be skipped entirely.

This commit also contains some refactoring to remove some code
duplication.

* cuda : fix editorconfig-checker warning

* sampling : use argmax for min-p sampling

* sampling : fix temperature check to allow zero temperature

This commit modifies the temperature sampling check to allow a
temperature value of zero. Previously, the check only allowed
positive temperature values, which excluded the valid case of
zero temperature.

The motivation for this is to enable a zero temperature setting which is
also currently causing the following test to fail:
```console
(venv) $ cd tools/server/tests
(venv) $ ./tests.sh unit/test_basic.py::test_load_split_model
```

* cuda : fix top-k compilation when CUB is unavailable

This commit adds a macro guard around argsort_f32_i32_cuda_cub usage
in the top-k fallback path, falling back to bitonic sort when
GGML_CUDA_USE_CUB is not defined.

The motivation for this is that some environments like AMD HIP
do not have CUB available, causing compilation failure.

Refs: https://github.com/ggml-org/llama.cpp/actions/runs/19728226426/job/56523606840#step:6:208

* sampling : add comments about backend sampler [no ci]

This commit adds a comment to llama_context's constructor explaining why
backend samplers are initialized early in the process.

* sampling : remove backend sampling chain from common_sampler

This commit removes the backend sampling chain from the common_sampler
structure and related functions.

The motivation for this change is that the backend samplers are not
currently set on the context, and if they are they would cause the
a graph reallocation to occur. Instead, the intialization is handled
like it currently is by llama_context's constructor.

* Fix top-k comp & behavior for non-CUB path

Some changes were made in 5ea3be265b
which were incomplete. In the case of non-CUB, bitonic sort and its
limitations of ncols < 1024 have to apply, similar to argsort.cu

* sampling : support intermixed backend/cpu samplers

This commit updates the backend sampling implementation to support
intermixed usage of backend and CPU samplers within the same batch.

The initial implementation was developed as an all-or-nothing solution:
either perform backend sampling for the entire batch, or perform CPU
sampling for the entire batch.

The motivation for this change is to support batches with mixed
sequences. For example, we may have a backend sampler configured for
sequence 0, while sequence 1 in the same batch uses CPU sampling. This
was not supported in the initial implementation.

This issue manifested in llama-server with the webui: decoding with
backend samplers would work initially, but after changing to CPU
sampling, a slot (sequence) could still be using a backend sampler.
This meant that logits in output_reserve would not be allocated,
resulting in an error.

The solution in this commit inspects the batch to determine which
sampling modes are needed and allocates buffers accordingly. However,
there is a known inefficiency: when we have intermixed backend/CPU
samplers in the same batch, we currently copy all logits to the host,
even for sequences using backend samplers.

Added test_backend_cpu_mixed_batch to verify correct behavior with
mixed backend/CPU samplers in a single batch, including dynamic
sampler switching between decode calls.

* squash! sampling : support intermixed backend/cpu samplers

Add check that logits is not null which is can happen for embeddings.

* squash! sampling : support intermixed backend/cpu samplers

Fix llama-save-load-state which currently fails by handling the case
when batch.logits is nullptr (like when loading state) by allocating
space for all outputs as CPU logits.

* refactor : simplify and improve memory management

* Add initial version for top-p sampling

As we only support static graphs for the time and we don't know the size
of the output of top-p, we have to do value-scaling same as for min-p
operator.

Further improvements can be applied to the unit-test (i.e. check for
equivalence of top_p happening on backend with top_p happening on cpu)
and also by constructing candidates and sorting those as opposed to
reversing the sort of the logits (this would be arange +
get_rows instead of argsort + get_rows)

* sampling : use logits directly for min-p filtering

* sampling : simplify

* llama : simplify

* llama : cleanup + naming

* llama : call backend_init once

* llama : reserve graphs with samplers

* llama : naming

* cont : naming

* sampling : lower log level for output buffer reallocations [no ci]

This commit changes the logging level for output buffer reallocations
in the llama_context::output_reserve function from INFO to DEBUG.

The motivation for this is that it currently logs to info and when
enabling verbose logging for llama-cli this will get mixed with the
output, for example:

```console
What is the capital of Sweden?output_reserve: reallocating output buffer from size 0.58 MiB to 1.74 MiB
 1. Stockholm
2\. Helsinki
Based are the options
1. Stockholm
Explanation: Stockholm is the capital of
...
```

* Fix backend_top_p_sampler

softmax(softmax) will return uniform distribution, so we should not
return the softmax but the logits instead.

* Factor out `ggml_sort` into its own function

* Make backend's top_p sampler inclusive

In addition to match the algorithm proposed in the original
[paper](https://arxiv.org/abs/1904.09751), this resolves the edge-case
where `max_p is > top_p` for a single logit, where the mask would
otherwise be empty (and we thus sample from the whole vocabulary with
equal likelihood)

* common : simplify sampler chain initialization

* sampling : do not create empty samplers

* sampling : fix top_p empty condition

* examples : remove outdated backend sampling section

This commit removes the outdated section about using backend samplers
from the README.md file in the examples/batched.

* sampling : fix backend temp sampler for zero temperature

This commit fixes the implementation of the temperature-based sampler
for the case when the temperature is set to zero. This now correctly
selects the most probable token by masking out all other tokens in the
logits.

* CUDA: Move cccl fetch to after cuda has been enabled in CMakeLists.txt

This will allow cccl to set build flags for the CUDA compiler, required
e.g. for MSVC compat, see also
https://github.com/NVIDIA/cccl/pull/6791

* CUDA: Use standard-compliant preprocessor for MSVC builds

Workarounds of https://github.com/NVIDIA/cccl/pull/6791 will not be
backported to CCCL 3.2, only the diagnostics/error messages will:
https://github.com/NVIDIA/cccl/pull/6827

* CUDA: Update CCCL's rc candidate

* squash! sampling : fix backend temp sampler for zero temperature

This modifies the parent commit to simply return the most probably token
instead of masking the logits.

* sampling : implement temp_ext_backend sampling

This commit implements the apply function for the extended temperature
sampling.

* sampling : minor cleanup

* sampling : stop short if backend sampler sampled a token

This commit modifies the graph building logic to immediately continue
when a token has already been sampled by the backend sampler.

It also updates the test for backend temporary sampling to include
top-k and distribution samplers in the chain to verify that they are not
producing any logits (they are not run).

* Revert "sampling : stop short if backend sampler sampled a token"

This reverts commit 87b2719eca.

* sampling : fix backend temp sampling to use logits masking

* sampling : simplify temp sampling

* sampling : remove redundant calls to ggml_build_forward_expand

* sampling : check backend support during init

* cont : keep backend sampling disabled for now

* sampling : fix outputs and device checks

* sampling : fix candidates logic

* Add perf-tests for CUMSUM

* Readd `cub::DeviceScan::InclusiveSum`-based CumSum

For single rows and large columns doing a for-loop over the function
`cub::DeviceScan::InclusiveSum` offered by CUB outperforms the
`cumsum_cub_kernel` where `cub::BlockScan` is used.

Numbers before this change

  Backend 1/3: CUDA0
  Device description: NVIDIA RTX 6000 Ada Generation
  Device memory: 48510 MB (48039 MB free)

  CUMSUM(type=f32,ne=[128,128,4,4]):                  311258 runs -     3.26 us/run -     2048 kB/run -  599.76 GB/s
  CUMSUM(type=f32,ne=[2048,16,5,4]):                  229390 runs -     4.40 us/run -     5120 kB/run - 1110.23 GB/s
  CUMSUM(type=f32,ne=[20000,10,4,1]):                  37583 runs -    29.63 us/run -     6250 kB/run -  201.18 GB/s
  CUMSUM(type=f32,ne=[128,1,1,1]):                    892819 runs -     1.12 us/run -        1 kB/run -    0.85 GB/s
  CUMSUM(type=f32,ne=[1024,1,1,1]):                   450505 runs -     2.25 us/run -        8 kB/run -    3.39 GB/s
  CUMSUM(type=f32,ne=[4096,1,1,1]):                   155629 runs -     6.61 us/run -       32 kB/run -    4.62 GB/s
  CUMSUM(type=f32,ne=[8192,1,1,1]):                    81910 runs -    12.60 us/run -       64 kB/run -    4.85 GB/s
  CUMSUM(type=f32,ne=[16384,1,1,1]):                   49146 runs -    23.99 us/run -      128 kB/run -    5.09 GB/s
  CUMSUM(type=f32,ne=[32768,1,1,1]):                   24573 runs -    47.10 us/run -      256 kB/run -    5.18 GB/s
  CUMSUM(type=f32,ne=[65536,1,1,1]):                   16382 runs -    93.57 us/run -      512 kB/run -    5.22 GB/s
  CUMSUM(type=f32,ne=[131072,1,1,1]):                   8191 runs -   184.79 us/run -     1024 kB/run -    5.29 GB/s
  CUMSUM(type=f32,ne=[200000,1,1,1]):                   8191 runs -   280.43 us/run -     1562 kB/run -    5.31 GB/s
  CUMSUM(type=f32,ne=[2000000,1,1,1]):                  2148 runs -  2771.23 us/run -    15625 kB/run -    5.38 GB/s
  CUMSUM(type=f32,ne=[128,4,1,1]):                    458696 runs -     2.21 us/run -        4 kB/run -    1.73 GB/s
  CUMSUM(type=f32,ne=[1024,4,1,1]):                   360404 runs -     2.82 us/run -       32 kB/run -   10.83 GB/s
  CUMSUM(type=f32,ne=[4096,4,1,1]):                   147438 runs -     7.12 us/run -      128 kB/run -   17.15 GB/s
  CUMSUM(type=f32,ne=[8192,4,1,1]):                    81910 runs -    12.90 us/run -      256 kB/run -   18.92 GB/s
  CUMSUM(type=f32,ne=[16384,4,1,1]):                   49146 runs -    24.32 us/run -      512 kB/run -   20.08 GB/s
  CUMSUM(type=f32,ne=[32768,4,1,1]):                   24573 runs -    47.28 us/run -     1024 kB/run -   20.66 GB/s
  CUMSUM(type=f32,ne=[65536,4,1,1]):                   16382 runs -    93.21 us/run -     2048 kB/run -   20.96 GB/s
  CUMSUM(type=f32,ne=[131072,4,1,1]):                   8191 runs -   185.04 us/run -     4096 kB/run -   21.11 GB/s
  CUMSUM(type=f32,ne=[200000,4,1,1]):                   5369 runs -   282.08 us/run -     6250 kB/run -   21.13 GB/s
  CUMSUM(type=f32,ne=[2000000,4,1,1]):                   537 runs -  2806.46 us/run -    62500 kB/run -   21.26 GB/s
  CUMSUM(type=f32,ne=[128,8,1,1]):                    458696 runs -     2.20 us/run -        8 kB/run -    3.47 GB/s
  CUMSUM(type=f32,ne=[1024,8,1,1]):                   360404 runs -     2.82 us/run -       64 kB/run -   21.66 GB/s
  CUMSUM(type=f32,ne=[4096,8,1,1]):                   147438 runs -     7.12 us/run -      256 kB/run -   34.28 GB/s
  CUMSUM(type=f32,ne=[8192,8,1,1]):                    81910 runs -    12.90 us/run -      512 kB/run -   37.84 GB/s
  CUMSUM(type=f32,ne=[16384,8,1,1]):                   49146 runs -    24.32 us/run -     1024 kB/run -   40.15 GB/s
  CUMSUM(type=f32,ne=[32768,8,1,1]):                   24573 runs -    47.28 us/run -     2048 kB/run -   41.31 GB/s
  CUMSUM(type=f32,ne=[65536,8,1,1]):                   16382 runs -    93.20 us/run -     4096 kB/run -   41.92 GB/s
  CUMSUM(type=f32,ne=[131072,8,1,1]):                   8194 runs -   185.05 us/run -     8192 kB/run -   42.22 GB/s
  CUMSUM(type=f32,ne=[200000,8,1,1]):                   5370 runs -   282.15 us/run -    12500 kB/run -   42.26 GB/s
  CUMSUM(type=f32,ne=[2000000,8,1,1]):                   269 runs -  4067.61 us/run -   125000 kB/run -   29.36 GB/s
  CUMSUM(type=f32,ne=[128,16,1,1]):                   303067 runs -     3.32 us/run -       16 kB/run -    4.60 GB/s
  CUMSUM(type=f32,ne=[1024,16,1,1]):                  303067 runs -     3.32 us/run -      128 kB/run -   36.76 GB/s
  CUMSUM(type=f32,ne=[4096,16,1,1]):                  147438 runs -     7.17 us/run -      512 kB/run -   68.13 GB/s
  CUMSUM(type=f32,ne=[8192,16,1,1]):                   81910 runs -    12.90 us/run -     1024 kB/run -   75.68 GB/s
  CUMSUM(type=f32,ne=[16384,16,1,1]):                  49146 runs -    24.33 us/run -     2048 kB/run -   80.28 GB/s
  CUMSUM(type=f32,ne=[32768,16,1,1]):                  24573 runs -    47.30 us/run -     4096 kB/run -   82.59 GB/s
  CUMSUM(type=f32,ne=[65536,16,1,1]):                  12291 runs -    93.24 us/run -     8192 kB/run -   83.80 GB/s
  CUMSUM(type=f32,ne=[131072,16,1,1]):                  6147 runs -   185.07 us/run -    16384 kB/run -   84.45 GB/s
  CUMSUM(type=f32,ne=[200000,16,1,1]):                  4029 runs -   282.40 us/run -    25000 kB/run -   84.46 GB/s
  CUMSUM(type=f32,ne=[2000000,16,1,1]):                  270 runs -  4118.40 us/run -   250000 kB/run -   58.11 GB/s
  Backend CUDA0: OK
Backend 2/3: CUDA1
  Device description: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
  Device memory: 97250 MB (96677 MB free)

  CUMSUM(type=f32,ne=[128,128,4,4]):                  368595 runs -     2.73 us/run -     2048 kB/run -  715.83 GB/s
  CUMSUM(type=f32,ne=[2048,16,5,4]):                  216282 runs -     4.72 us/run -     5120 kB/run - 1035.32 GB/s
  CUMSUM(type=f32,ne=[20000,10,4,1]):                  32214 runs -    34.33 us/run -     6250 kB/run -  173.64 GB/s
  CUMSUM(type=f32,ne=[128,1,1,1]):                    810909 runs -     1.24 us/run -        1 kB/run -    0.77 GB/s
  CUMSUM(type=f32,ne=[1024,1,1,1]):                   401359 runs -     2.52 us/run -        8 kB/run -    3.03 GB/s
  CUMSUM(type=f32,ne=[4096,1,1,1]):                   139247 runs -     7.44 us/run -       32 kB/run -    4.10 GB/s
  CUMSUM(type=f32,ne=[8192,1,1,1]):                    73719 runs -    14.27 us/run -       64 kB/run -    4.28 GB/s
  CUMSUM(type=f32,ne=[16384,1,1,1]):                   40955 runs -    27.24 us/run -      128 kB/run -    4.48 GB/s
  CUMSUM(type=f32,ne=[32768,1,1,1]):                   24573 runs -    53.46 us/run -      256 kB/run -    4.57 GB/s
  CUMSUM(type=f32,ne=[65536,1,1,1]):                   16382 runs -   105.29 us/run -      512 kB/run -    4.64 GB/s
  CUMSUM(type=f32,ne=[131072,1,1,1]):                   8191 runs -   210.15 us/run -     1024 kB/run -    4.65 GB/s
  CUMSUM(type=f32,ne=[200000,1,1,1]):                   8191 runs -   318.22 us/run -     1562 kB/run -    4.68 GB/s
  CUMSUM(type=f32,ne=[2000000,1,1,1]):                  2148 runs -  3142.23 us/run -    15625 kB/run -    4.74 GB/s
  CUMSUM(type=f32,ne=[128,4,1,1]):                    303067 runs -     3.34 us/run -        4 kB/run -    1.14 GB/s
  CUMSUM(type=f32,ne=[1024,4,1,1]):                   253921 runs -     4.03 us/run -       32 kB/run -    7.58 GB/s
  CUMSUM(type=f32,ne=[4096,4,1,1]):                   122865 runs -     8.20 us/run -      128 kB/run -   14.89 GB/s
  CUMSUM(type=f32,ne=[8192,4,1,1]):                    73719 runs -    14.96 us/run -      256 kB/run -   16.32 GB/s
  CUMSUM(type=f32,ne=[16384,4,1,1]):                   40955 runs -    28.66 us/run -      512 kB/run -   17.04 GB/s
  CUMSUM(type=f32,ne=[32768,4,1,1]):                   24573 runs -    54.21 us/run -     1024 kB/run -   18.01 GB/s
  CUMSUM(type=f32,ne=[65536,4,1,1]):                   16382 runs -   106.49 us/run -     2048 kB/run -   18.34 GB/s
  CUMSUM(type=f32,ne=[131072,4,1,1]):                   8191 runs -   210.88 us/run -     4096 kB/run -   18.52 GB/s
  CUMSUM(type=f32,ne=[200000,4,1,1]):                   5369 runs -   321.77 us/run -     6250 kB/run -   18.53 GB/s
  CUMSUM(type=f32,ne=[2000000,4,1,1]):                   537 runs -  3191.79 us/run -    62500 kB/run -   18.69 GB/s
  CUMSUM(type=f32,ne=[128,8,1,1]):                    376786 runs -     2.67 us/run -        8 kB/run -    2.86 GB/s
  CUMSUM(type=f32,ne=[1024,8,1,1]):                   245730 runs -     4.10 us/run -       64 kB/run -   14.90 GB/s
  CUMSUM(type=f32,ne=[4096,8,1,1]):                   122865 runs -     8.20 us/run -      256 kB/run -   29.79 GB/s
  CUMSUM(type=f32,ne=[8192,8,1,1]):                    65528 runs -    16.38 us/run -      512 kB/run -   29.82 GB/s
  CUMSUM(type=f32,ne=[16384,8,1,1]):                   40955 runs -    28.69 us/run -     1024 kB/run -   34.04 GB/s
  CUMSUM(type=f32,ne=[32768,8,1,1]):                   24573 runs -    55.28 us/run -     2048 kB/run -   35.33 GB/s
  CUMSUM(type=f32,ne=[65536,8,1,1]):                   16382 runs -   108.50 us/run -     4096 kB/run -   36.00 GB/s
  CUMSUM(type=f32,ne=[131072,8,1,1]):                   8194 runs -   213.75 us/run -     8192 kB/run -   36.55 GB/s
  CUMSUM(type=f32,ne=[200000,8,1,1]):                   5370 runs -   326.31 us/run -    12500 kB/run -   36.54 GB/s
  CUMSUM(type=f32,ne=[2000000,8,1,1]):                   538 runs -  3252.68 us/run -   125000 kB/run -   36.72 GB/s
  CUMSUM(type=f32,ne=[128,16,1,1]):                   303067 runs -     3.32 us/run -       16 kB/run -    4.60 GB/s
  CUMSUM(type=f32,ne=[1024,16,1,1]):                  253921 runs -     4.06 us/run -      128 kB/run -   30.09 GB/s
  CUMSUM(type=f32,ne=[4096,16,1,1]):                  122865 runs -     8.20 us/run -      512 kB/run -   59.57 GB/s
  CUMSUM(type=f32,ne=[8192,16,1,1]):                   65528 runs -    16.38 us/run -     1024 kB/run -   59.63 GB/s
  CUMSUM(type=f32,ne=[16384,16,1,1]):                  40955 runs -    28.69 us/run -     2048 kB/run -   68.09 GB/s
  CUMSUM(type=f32,ne=[32768,16,1,1]):                  24573 runs -    55.28 us/run -     4096 kB/run -   70.67 GB/s
  CUMSUM(type=f32,ne=[65536,16,1,1]):                  12291 runs -   108.50 us/run -     8192 kB/run -   72.02 GB/s
  CUMSUM(type=f32,ne=[131072,16,1,1]):                  6147 runs -   213.60 us/run -    16384 kB/run -   73.17 GB/s
  CUMSUM(type=f32,ne=[200000,16,1,1]):                  4029 runs -   326.04 us/run -    25000 kB/run -   73.15 GB/s
  CUMSUM(type=f32,ne=[2000000,16,1,1]):                  270 runs -  5458.69 us/run -   250000 kB/run -   43.84 GB/s

----
Numbers after:

Backend 1/3: CUDA0
  Device description: NVIDIA RTX 6000 Ada Generation
  Device memory: 48510 MB (48039 MB free)

  CUMSUM(type=f32,ne=[128,128,4,4]):                  311258 runs -     3.25 us/run -     2048 kB/run -  601.62 GB/s
  CUMSUM(type=f32,ne=[2048,16,5,4]):                  229390 runs -     4.40 us/run -     5120 kB/run - 1110.14 GB/s
  CUMSUM(type=f32,ne=[20000,10,4,1]):                  37583 runs -    29.67 us/run -     6250 kB/run -  200.89 GB/s
  CUMSUM(type=f32,ne=[128,1,1,1]):                    892819 runs -     1.12 us/run -        1 kB/run -    0.85 GB/s
  CUMSUM(type=f32,ne=[1024,1,1,1]):                   458696 runs -     2.21 us/run -        8 kB/run -    3.45 GB/s
  CUMSUM(type=f32,ne=[4096,1,1,1]):                   376786 runs -     2.66 us/run -       32 kB/run -   11.46 GB/s
  CUMSUM(type=f32,ne=[8192,1,1,1]):                   393168 runs -     2.59 us/run -       64 kB/run -   23.57 GB/s
  CUMSUM(type=f32,ne=[16384,1,1,1]):                  393168 runs -     2.59 us/run -      128 kB/run -   47.15 GB/s
  CUMSUM(type=f32,ne=[32768,1,1,1]):                  376786 runs -     2.69 us/run -      256 kB/run -   90.69 GB/s
  CUMSUM(type=f32,ne=[65536,1,1,1]):                  327640 runs -     3.06 us/run -      512 kB/run -  159.65 GB/s
  CUMSUM(type=f32,ne=[131072,1,1,1]):                 311258 runs -     3.28 us/run -     1024 kB/run -  297.77 GB/s
  CUMSUM(type=f32,ne=[200000,1,1,1]):                 270303 runs -     3.74 us/run -     1562 kB/run -  398.14 GB/s
  CUMSUM(type=f32,ne=[2000000,1,1,1]):                137472 runs -     7.35 us/run -    15625 kB/run - 2026.94 GB/s
  CUMSUM(type=f32,ne=[128,4,1,1]):                    876437 runs -     1.14 us/run -        4 kB/run -    3.33 GB/s
  CUMSUM(type=f32,ne=[1024,4,1,1]):                   442314 runs -     2.28 us/run -       32 kB/run -   13.39 GB/s
  CUMSUM(type=f32,ne=[4096,4,1,1]):                   155629 runs -     6.69 us/run -      128 kB/run -   18.24 GB/s
  CUMSUM(type=f32,ne=[8192,4,1,1]):                    81910 runs -    12.53 us/run -      256 kB/run -   19.49 GB/s
  CUMSUM(type=f32,ne=[16384,4,1,1]):                   49146 runs -    24.18 us/run -      512 kB/run -   20.20 GB/s
  CUMSUM(type=f32,ne=[32768,4,1,1]):                   65528 runs -    15.34 us/run -     1024 kB/run -   63.66 GB/s
  CUMSUM(type=f32,ne=[65536,4,1,1]):                   73719 runs -    14.76 us/run -     2048 kB/run -  132.35 GB/s
  CUMSUM(type=f32,ne=[131072,4,1,1]):                  65528 runs -    16.01 us/run -     4096 kB/run -  244.07 GB/s
  CUMSUM(type=f32,ne=[200000,4,1,1]):                  64428 runs -    16.51 us/run -     6250 kB/run -  360.97 GB/s
  CUMSUM(type=f32,ne=[2000000,4,1,1]):                 33831 runs -    29.59 us/run -    62500 kB/run - 2016.08 GB/s
  CUMSUM(type=f32,ne=[128,8,1,1]):                    868246 runs -     1.16 us/run -        8 kB/run -    6.59 GB/s
  CUMSUM(type=f32,ne=[1024,8,1,1]):                   442314 runs -     2.28 us/run -       64 kB/run -   26.76 GB/s
  CUMSUM(type=f32,ne=[4096,8,1,1]):                   155629 runs -     6.69 us/run -      256 kB/run -   36.48 GB/s
  CUMSUM(type=f32,ne=[8192,8,1,1]):                    81910 runs -    12.53 us/run -      512 kB/run -   38.97 GB/s
  CUMSUM(type=f32,ne=[16384,8,1,1]):                   49146 runs -    24.17 us/run -     1024 kB/run -   40.41 GB/s
  CUMSUM(type=f32,ne=[32768,8,1,1]):                   24573 runs -    47.53 us/run -     2048 kB/run -   41.10 GB/s
  CUMSUM(type=f32,ne=[65536,8,1,1]):                   16382 runs -    61.25 us/run -     4096 kB/run -   63.77 GB/s
  CUMSUM(type=f32,ne=[131072,8,1,1]):                  32776 runs -    31.79 us/run -     8192 kB/run -  245.82 GB/s
  CUMSUM(type=f32,ne=[200000,8,1,1]):                  32220 runs -    32.90 us/run -    12500 kB/run -  362.35 GB/s
  CUMSUM(type=f32,ne=[2000000,8,1,1]):                  6725 runs -   151.99 us/run -   125000 kB/run -  785.77 GB/s
  CUMSUM(type=f32,ne=[128,16,1,1]):                   851864 runs -     1.18 us/run -       16 kB/run -   12.97 GB/s
  CUMSUM(type=f32,ne=[1024,16,1,1]):                  442314 runs -     2.30 us/run -      128 kB/run -   53.13 GB/s
  CUMSUM(type=f32,ne=[4096,16,1,1]):                  155629 runs -     6.68 us/run -      512 kB/run -   73.13 GB/s
  CUMSUM(type=f32,ne=[8192,16,1,1]):                   81910 runs -    12.68 us/run -     1024 kB/run -   77.00 GB/s
  CUMSUM(type=f32,ne=[16384,16,1,1]):                  40955 runs -    24.56 us/run -     2048 kB/run -   79.53 GB/s
  CUMSUM(type=f32,ne=[32768,16,1,1]):                  24573 runs -    47.52 us/run -     4096 kB/run -   82.21 GB/s
  CUMSUM(type=f32,ne=[65536,16,1,1]):                  12291 runs -    93.44 us/run -     8192 kB/run -   83.62 GB/s
  CUMSUM(type=f32,ne=[131072,16,1,1]):                 16392 runs -    63.36 us/run -    16384 kB/run -  246.68 GB/s
  CUMSUM(type=f32,ne=[200000,16,1,1]):                 16116 runs -    65.25 us/run -    25000 kB/run -  365.53 GB/s
  CUMSUM(type=f32,ne=[2000000,16,1,1]):                 3375 runs -   304.46 us/run -   250000 kB/run -  785.98 GB/s
  Backend CUDA0: OK
Backend 2/3: CUDA1
  Device description: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
  Device memory: 97250 MB (96677 MB free)

  CUMSUM(type=f32,ne=[128,128,4,4]):                  376786 runs -     2.69 us/run -     2048 kB/run -  727.04 GB/s
  CUMSUM(type=f32,ne=[2048,16,5,4]):                  216282 runs -     4.64 us/run -     5120 kB/run - 1053.30 GB/s
  CUMSUM(type=f32,ne=[20000,10,4,1]):                  32214 runs -    34.21 us/run -     6250 kB/run -  174.27 GB/s
  CUMSUM(type=f32,ne=[128,1,1,1]):                    819100 runs -     1.22 us/run -        1 kB/run -    0.78 GB/s
  CUMSUM(type=f32,ne=[1024,1,1,1]):                   409550 runs -     2.47 us/run -        8 kB/run -    3.09 GB/s
  CUMSUM(type=f32,ne=[4096,1,1,1]):                   303067 runs -     3.31 us/run -       32 kB/run -    9.21 GB/s
  CUMSUM(type=f32,ne=[8192,1,1,1]):                   237539 runs -     4.33 us/run -       64 kB/run -   14.08 GB/s
  CUMSUM(type=f32,ne=[16384,1,1,1]):                  237539 runs -     4.33 us/run -      128 kB/run -   28.17 GB/s
  CUMSUM(type=f32,ne=[32768,1,1,1]):                  188393 runs -     5.37 us/run -      256 kB/run -   45.47 GB/s
  CUMSUM(type=f32,ne=[65536,1,1,1]):                  188393 runs -     5.41 us/run -      512 kB/run -   90.20 GB/s
  CUMSUM(type=f32,ne=[131072,1,1,1]):                 188393 runs -     5.41 us/run -     1024 kB/run -  180.41 GB/s
  CUMSUM(type=f32,ne=[200000,1,1,1]):                 188393 runs -     5.41 us/run -     1562 kB/run -  275.27 GB/s
  CUMSUM(type=f32,ne=[2000000,1,1,1]):                128880 runs -     7.76 us/run -    15625 kB/run - 1920.33 GB/s
  CUMSUM(type=f32,ne=[128,4,1,1]):                    802718 runs -     1.26 us/run -        4 kB/run -    3.03 GB/s
  CUMSUM(type=f32,ne=[1024,4,1,1]):                   401359 runs -     2.51 us/run -       32 kB/run -   12.18 GB/s
  CUMSUM(type=f32,ne=[4096,4,1,1]):                   139247 runs -     7.51 us/run -      128 kB/run -   16.26 GB/s
  CUMSUM(type=f32,ne=[8192,4,1,1]):                    73719 runs -    14.17 us/run -      256 kB/run -   17.23 GB/s
  CUMSUM(type=f32,ne=[16384,4,1,1]):                   40955 runs -    27.37 us/run -      512 kB/run -   17.84 GB/s
  CUMSUM(type=f32,ne=[32768,4,1,1]):                   40955 runs -    26.33 us/run -     1024 kB/run -   37.10 GB/s
  CUMSUM(type=f32,ne=[65536,4,1,1]):                   40955 runs -    26.19 us/run -     2048 kB/run -   74.59 GB/s
  CUMSUM(type=f32,ne=[131072,4,1,1]):                  40955 runs -    26.35 us/run -     4096 kB/run -  148.26 GB/s
  CUMSUM(type=f32,ne=[200000,4,1,1]):                  42952 runs -    24.18 us/run -     6250 kB/run -  246.51 GB/s
  CUMSUM(type=f32,ne=[2000000,4,1,1]):                 32757 runs -    31.01 us/run -    62500 kB/run - 1923.68 GB/s
  CUMSUM(type=f32,ne=[128,8,1,1]):                    786336 runs -     1.28 us/run -        8 kB/run -    5.95 GB/s
  CUMSUM(type=f32,ne=[1024,8,1,1]):                   393168 runs -     2.57 us/run -       64 kB/run -   23.73 GB/s
  CUMSUM(type=f32,ne=[4096,8,1,1]):                   131056 runs -     7.67 us/run -      256 kB/run -   31.82 GB/s
  CUMSUM(type=f32,ne=[8192,8,1,1]):                    73719 runs -    14.43 us/run -      512 kB/run -   33.84 GB/s
  CUMSUM(type=f32,ne=[16384,8,1,1]):                   40955 runs -    27.90 us/run -     1024 kB/run -   35.01 GB/s
  CUMSUM(type=f32,ne=[32768,8,1,1]):                   24573 runs -    54.63 us/run -     2048 kB/run -   35.75 GB/s
  CUMSUM(type=f32,ne=[65536,8,1,1]):                   16382 runs -    72.24 us/run -     4096 kB/run -   54.08 GB/s
  CUMSUM(type=f32,ne=[131072,8,1,1]):                  20485 runs -    52.66 us/run -     8192 kB/run -  148.37 GB/s
  CUMSUM(type=f32,ne=[200000,8,1,1]):                  21480 runs -    48.00 us/run -    12500 kB/run -  248.42 GB/s
  CUMSUM(type=f32,ne=[2000000,8,1,1]):                 16140 runs -    61.99 us/run -   125000 kB/run - 1926.51 GB/s
  CUMSUM(type=f32,ne=[128,16,1,1]):                   786336 runs -     1.28 us/run -       16 kB/run -   11.90 GB/s
  CUMSUM(type=f32,ne=[1024,16,1,1]):                  393168 runs -     2.57 us/run -      128 kB/run -   47.57 GB/s
  CUMSUM(type=f32,ne=[4096,16,1,1]):                  131056 runs -     7.65 us/run -      512 kB/run -   63.83 GB/s
  CUMSUM(type=f32,ne=[8192,16,1,1]):                   73719 runs -    14.42 us/run -     1024 kB/run -   67.74 GB/s
  CUMSUM(type=f32,ne=[16384,16,1,1]):                  40955 runs -    27.87 us/run -     2048 kB/run -   70.09 GB/s
  CUMSUM(type=f32,ne=[32768,16,1,1]):                  24573 runs -    54.54 us/run -     4096 kB/run -   71.63 GB/s
  CUMSUM(type=f32,ne=[65536,16,1,1]):                  12291 runs -   107.53 us/run -     8192 kB/run -   72.66 GB/s
  CUMSUM(type=f32,ne=[131072,16,1,1]):                 10245 runs -   105.10 us/run -    16384 kB/run -  148.70 GB/s
  CUMSUM(type=f32,ne=[200000,16,1,1]):                 10744 runs -    95.36 us/run -    25000 kB/run -  250.11 GB/s
  CUMSUM(type=f32,ne=[2000000,16,1,1]):                 5400 runs -   186.97 us/run -   250000 kB/run - 1279.90 GB/s

* sampling : expand support (wip)

* tests : fix memory leaks

* cont : fixes

* tests : check temp back to 0.0

* sampling : fix top-p

* sampling : handle n_probs case

* server : handle unsupported cases

* metal : print node names for debugging

* ggml : remove redundant src in ggml_cast

* ggml-alloc : fix reuse-parent logic for misaligned sizes

* Revert "ggml : remove redundant src in ggml_cast"

This reverts commit 62d1b0082d.

* CUDA: Add Cooperative-Groups-based parallelization of ncols in softmax

Old implementation parallelizes rows across SMs, which does not fit the
needs of backend-sampling (where we have ncols >> nrows and thus want to
parallelize ncols across SMs)

* Add TODOs to and adjust heuristics of row-wise soft_max in CUDA

Heuristics were selected based on the following numbers:

```
-- Before
Backend 1/2: CUDA0
  Device description: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
  Device memory: 97250 MB (96691 MB free)

  SOFT_MAX(type=f32,ne=[4096,4096,5,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                2236 runs -   450.34 us/run -   655360 kB/run - 1401.20 GB/s
  SOFT_MAX(type=f32,ne=[12888,256,5,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):               17748 runs -    56.80 us/run -   128880 kB/run - 2168.19 GB/s
  SOFT_MAX(type=f32,ne=[77,4096,5,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 57204 runs -    18.35 us/run -    12320 kB/run -  640.57 GB/s
  SOFT_MAX(type=f32,ne=[1024,1024,10,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):               9840 runs -   102.46 us/run -    81920 kB/run -  763.45 GB/s
  SOFT_MAX(type=f32,ne=[77,1024,10,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                98064 runs -    10.25 us/run -     6160 kB/run -  573.43 GB/s
  SOFT_MAX(type=f32,ne=[256,256,20,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                98310 runs -    10.25 us/run -    10240 kB/run -  953.20 GB/s
  SOFT_MAX(type=f32,ne=[64,64,20,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 172011 runs -     5.99 us/run -      640 kB/run -  101.84 GB/s
  SOFT_MAX(type=f32,ne=[77,64,20,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 172011 runs -     5.97 us/run -      770 kB/run -  123.02 GB/s
  SOFT_MAX(type=f32,ne=[8192,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 172011 runs -     6.00 us/run -       64 kB/run -   10.16 GB/s
  SOFT_MAX(type=f32,ne=[8192,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 163820 runs -     6.12 us/run -      256 kB/run -   39.91 GB/s
  SOFT_MAX(type=f32,ne=[8192,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                147438 runs -     6.88 us/run -     1024 kB/run -  141.92 GB/s
  SOFT_MAX(type=f32,ne=[16384,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                122865 runs -     8.20 us/run -      128 kB/run -   14.89 GB/s
  SOFT_MAX(type=f32,ne=[16384,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                114674 runs -     8.87 us/run -      512 kB/run -   55.06 GB/s
  SOFT_MAX(type=f32,ne=[16384,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                98292 runs -    10.24 us/run -     2048 kB/run -  190.82 GB/s
  SOFT_MAX(type=f32,ne=[32768,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 49146 runs -    21.37 us/run -      256 kB/run -   11.43 GB/s
  SOFT_MAX(type=f32,ne=[32768,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 49146 runs -    22.54 us/run -     1024 kB/run -   43.33 GB/s
  SOFT_MAX(type=f32,ne=[32768,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                49146 runs -    23.92 us/run -     4096 kB/run -  163.32 GB/s
  SOFT_MAX(type=f32,ne=[65536,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 32764 runs -    38.94 us/run -      512 kB/run -   12.54 GB/s
  SOFT_MAX(type=f32,ne=[65536,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 24573 runs -    41.94 us/run -     2048 kB/run -   46.57 GB/s
  SOFT_MAX(type=f32,ne=[65536,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                24582 runs -    43.09 us/run -     8192 kB/run -  181.32 GB/s
  SOFT_MAX(type=f32,ne=[131072,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                16382 runs -    74.56 us/run -     1024 kB/run -   13.10 GB/s
  SOFT_MAX(type=f32,ne=[131072,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                16382 runs -    79.85 us/run -     4096 kB/run -   48.92 GB/s
  SOFT_MAX(type=f32,ne=[131072,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):               12294 runs -    82.41 us/run -    16384 kB/run -  189.64 GB/s
  SOFT_MAX(type=f32,ne=[262144,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 8191 runs -   145.16 us/run -     2048 kB/run -   13.46 GB/s
  SOFT_MAX(type=f32,ne=[262144,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 8194 runs -   155.46 us/run -     8192 kB/run -   50.26 GB/s
  SOFT_MAX(type=f32,ne=[262144,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                7175 runs -   160.70 us/run -    32768 kB/run -  194.56 GB/s
  SOFT_MAX(type=f32,ne=[524288,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 8191 runs -   285.81 us/run -     4096 kB/run -   13.67 GB/s
  SOFT_MAX(type=f32,ne=[524288,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 4098 runs -   306.91 us/run -    16384 kB/run -   50.92 GB/s
  SOFT_MAX(type=f32,ne=[524288,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                3591 runs -   317.06 us/run -    65536 kB/run -  197.32 GB/s

-- After
Backend 1/2: CUDA0
  Device description: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
  Device memory: 97250 MB (96691 MB free)

  SOFT_MAX(type=f32,ne=[4096,4096,5,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                2236 runs -   450.67 us/run -   655360 kB/run - 1400.15 GB/s
  SOFT_MAX(type=f32,ne=[12888,256,5,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):               17748 runs -    56.97 us/run -   128880 kB/run - 2161.50 GB/s
  SOFT_MAX(type=f32,ne=[77,4096,5,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 57204 runs -    18.35 us/run -    12320 kB/run -  640.36 GB/s
  SOFT_MAX(type=f32,ne=[1024,1024,10,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):               9840 runs -   102.46 us/run -    81920 kB/run -  763.42 GB/s
  SOFT_MAX(type=f32,ne=[77,1024,10,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                98064 runs -    10.25 us/run -     6160 kB/run -  573.43 GB/s
  SOFT_MAX(type=f32,ne=[256,256,20,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                98310 runs -    10.25 us/run -    10240 kB/run -  953.21 GB/s
  SOFT_MAX(type=f32,ne=[64,64,20,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 147438 runs -     7.00 us/run -      640 kB/run -   87.26 GB/s
  SOFT_MAX(type=f32,ne=[77,64,20,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 147438 runs -     6.99 us/run -      770 kB/run -  105.05 GB/s
  SOFT_MAX(type=f32,ne=[8192,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 172011 runs -     6.02 us/run -       64 kB/run -   10.13 GB/s
  SOFT_MAX(type=f32,ne=[8192,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 163820 runs -     6.12 us/run -      256 kB/run -   39.87 GB/s
  SOFT_MAX(type=f32,ne=[8192,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                147438 runs -     6.91 us/run -     1024 kB/run -  141.40 GB/s
  SOFT_MAX(type=f32,ne=[16384,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                122865 runs -     8.20 us/run -      128 kB/run -   14.89 GB/s
  SOFT_MAX(type=f32,ne=[16384,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                114674 runs -     8.79 us/run -      512 kB/run -   55.54 GB/s
  SOFT_MAX(type=f32,ne=[16384,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                98292 runs -    10.24 us/run -     2048 kB/run -  190.82 GB/s
  SOFT_MAX(type=f32,ne=[32768,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                131056 runs -     8.11 us/run -      256 kB/run -   30.12 GB/s
  SOFT_MAX(type=f32,ne=[32768,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 49146 runs -    22.54 us/run -     1024 kB/run -   43.33 GB/s
  SOFT_MAX(type=f32,ne=[32768,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                49146 runs -    23.32 us/run -     4096 kB/run -  167.50 GB/s
  SOFT_MAX(type=f32,ne=[65536,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                122865 runs -     8.19 us/run -      512 kB/run -   59.63 GB/s
  SOFT_MAX(type=f32,ne=[65536,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                 40955 runs -    24.59 us/run -     2048 kB/run -   79.43 GB/s
  SOFT_MAX(type=f32,ne=[65536,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                24582 runs -    43.21 us/run -     8192 kB/run -  180.84 GB/s
  SOFT_MAX(type=f32,ne=[131072,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):               122865 runs -     8.19 us/run -     1024 kB/run -  119.25 GB/s
  SOFT_MAX(type=f32,ne=[131072,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                40955 runs -    24.59 us/run -     4096 kB/run -  158.87 GB/s
  SOFT_MAX(type=f32,ne=[131072,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):               12294 runs -    82.37 us/run -    16384 kB/run -  189.74 GB/s
  SOFT_MAX(type=f32,ne=[262144,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):               122865 runs -     8.20 us/run -     2048 kB/run -  238.28 GB/s
  SOFT_MAX(type=f32,ne=[262144,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                36873 runs -    28.66 us/run -     8192 kB/run -  272.61 GB/s
  SOFT_MAX(type=f32,ne=[262144,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                9225 runs -   108.51 us/run -    32768 kB/run -  288.13 GB/s
  SOFT_MAX(type=f32,ne=[524288,1,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                98292 runs -    10.24 us/run -     4096 kB/run -  381.65 GB/s
  SOFT_MAX(type=f32,ne=[524288,4,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                32784 runs -    31.74 us/run -    16384 kB/run -  492.43 GB/s
  SOFT_MAX(type=f32,ne=[524288,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000,inplace=0):                8721 runs -   121.20 us/run -    65536 kB/run -  516.19 GB/s
```

* Fix compiler warnings by casting `const` away

* llama : require backend samplers to be of type llama_sampler_chain

* sampling : use host buffer type for inputs

* Try fixing HIP build errors by adding corresponding #defines

Will likely have to disable for MUSA as I didn't find any docs online

* Fix launch logic when supports_cooperative_launch=false

* Disable cooperative groups for musa

Didn't find any doc online, so I don't even know if they support this

* server : reconnect the backend_sampling setting in the WebUI

* graph : make the compute graph constant with respect to active samplers

* batch : fix sequence id ownage

* graph : respect sampler order for graph reuse

* HIP/MUSA: fix build for backend sampling

* sampling : optimize logit_bias sampler

* cont : fix build

* sampling : generic ggml op support detection

* sampling : fix greedy

* tests : run backend sampler tests always on the CPU

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* webui : fix lint

* Fix data-race in `soft_max_f32_parallelize_cols_single_row`

By using `tmp_vals` to store both max values and exponential
accumulator there was a potential data-race, where the exponential accumulator
for a given CTA may have written to `tmp_vals` before all others CTAs have
read the max value from it.

To avoid a third g.sync(), an additional temporary data-storage was
added. Given that there are syncs in place after writing to gmem, it is
guaranteed that the previous values for sums/max were read by all CTAs now.

* Apply automated code-formating to softmax.cu

* llama : clarify backend_accept/backend_set_input comments [no ci]

* llama : fix typo in comment [no ci]

* tests : use smart pointers for backend samplers

* tests : use smart pointers for model and context

* tests : remove vocab member from test_model_context

Also includes some minor cleanups related to nullptr checks.

* tests : extract batch info update to separate method

* tests : fix batch token position tracking in test_backend_sampler.cpp

* tests : add --device option support to backend sampler tests

This commit adds support for specifying a device to run the test on.

* common : disable backend sampling when grammar is involved

* Fix different RNG-states between backend-sampling and llama-sampling

By default, we perform a warm-up step where the ggml_cgraph is computed
once. For backend-sampling, this graph contains the sampler, and thus
the RNG state of the backend's dist sampler is advanced once.

Solution to this is to reset the samplers after the warmup has finished

* Make backend dist sampler use same rnd's as dist sampler

We sample in double precision and cast to float to match rnd numbers of
llama_dampler_dist which uses double precision (sampling from
std::uniform_real_distribution<double> and
std::uniform_real_distribution<float> with same rng will produce
different sequences).

* Update CCCL version to v3.2.0-rc2

* Build with CCCL 3.2 for CUDA backends

Gives best perf for backend-sampling on CUDA. Flag can be removed once
CCCL 3.2 is bundled within CTK and that CTK version is used in llama.cpp

* tests : revert server test changes (no longer needed)

* ggml : include cub/cub.cuh instead of block_scan.cuh

This commit updates the include directive in cumsum.cu to use
cub/cub.cuh instead of cub/block/block_scan.cuh.

The motivation of this change is that without it compilation fails
with the following error:
```console
/llama.cpp/ggml/src/ggml-cuda/cumsum.cu(196): error: name followed by "::" must be a class or namespace name
      cub::DeviceScan::InclusiveSum(nullptr,
           ^

/llama.cpp/ggml/src/ggml-cuda/cumsum.cu(207): error: name followed by "::" must be a class or namespace name
      cub::DeviceScan::InclusiveSum((void *) tmp_alloc.get(), tmp_size, src, dst, ne, stream);
           ^

2 errors detected in the compilation of "/llama.cpp/ggml/src/ggml-cuda/cumsum.cu".
gmake[2]: *** [ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/build.make:317: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cumsum.cu.o] Error 2
```
Commit 83b3b1c271 ("cuda: optimize
cumsum cub path (#18362)") updated the include directive replacing
device_scan.cuh which is causing this issue.

This commit uses cub/cub.cuh umbrella header which is consistent with
other files in the ggml-cuda directory like mean.cu, sum.cu, etc.

* arg : add shorthand for --backend-sampling

* ci : add server workflow with backend sampling

* sampling : fix reshapes

* server : remove printfs

* sampling : zero-initialize input buffers

* minor : add comments + some cleanup

* llama : assert at most one output token per sequence

* tests : add more top_k tests

* CUDA: Fix non-determinism of CUB-based Top-K

DeviceTopK::MaxPairs is an iterative algorithm, where `d_keys_out` is
written after every iteration. As a consequence, it must not overlap
with `d_keys_in`, or otherwise undefined behavior occurs (keys are no
longer unique in d_keys_in and may map to different values between
iterations)

* CUDA: Optimize index of top_k_cub

By using the fancy
[`counting_iterator`](https://nvidia.github.io/cccl/thrust/api/classthrust_1_1counting__iterator.html#classthrust_1_1counting__iterator)
exposed by CCCL, we can avoid materializing the index to GPU memory,
saving VRAM + 1 kernel invocation

* Apply code-formatting to top-k.cu

* CUDA: Remove obsolete temp_keys from CUB

Since we use cuda::discard_iterator to avoid writing out the keys, we
can directly pass in src instead of copying it to `temp_keys`

* minor : cleanup, TODOs, etc.

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Oliver Simons <osimons@nvidia.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
 2026-01-04 22:22:16 +02:00
Prabod 5755e52d15 model : Maincoder-1B support (#18534) 
* Add Maincoder model support

* Removed SPM model vocabulary setting and MOE related GGUF parameters
Removed trailing spaces from maincoder.cpp

* removed set_vocab

* added new line

* Fix formatting

* Add a new line for PEP8
 2026-01-02 20:11:59 +01:00
Sigbjørn Skjæret 169ee68ffb model : remove modern-bert iswa template (#18529) 
* remove modern-bert iswa template

* forgotten
 2026-01-02 00:06:42 +01:00
tt ced765be44 model: support youtu-vl model (#18479) 
* Support Youtu-VL Model

* merge code

* fix bug

* revert qwen2 code & support rsplit in minja.hpp

* update warm info

* fix annotation

* u

* revert minja.hpp

* fix

* Do not write routed_scaling_factor to gguf when routed_scaling_factor is None

* fix expert_weights_scale

* LGTM after whitespace fixes

* fix

* fix

* fix

* layers to layer_index

* enum fix

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-01-01 19:25:54 +01:00
o7si d0a6a31470 model : add support for JinaBertModel with non-gated ffn (#18475) 
* WIP: Initial commit for fixing JinaBert original FF type support

* convert: add jina-v2-de tokenizer variant for German_Semantic_V3

* convert: fix token collision in BERT phantom vocab conversion

* convert: add feed_forward_type metadata

* model: add feed_forward_type metadata for jina-bert-v2

* model: jina-bert-v2 support standard GELU FFN variant

* model: remove ffn_type, detect FFN variant from tensor dimensions

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/models/bert.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/models/bert.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* revert collision fix to be handled in separate PR

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-01-01 18:38:51 +01:00
HelloKS f4f5019254 model: add Solar Open model (#18511) 
* model: add Solar-Open model

* vocab: add solar-open to end eog blacklist

* model: add proper llm type

* chat: basic template for solar open

* typo: fix comment about vocab

* convert: sugested changes

* convert: suggested changes

* chat: change reasoning end tag for solar-open

* llama-chat: add solar-open template
 2026-01-01 18:01:43 +01:00
momonga 9c675c7140 model : Plamo3 support (#17304) 
* plamo3

* fix plamo3

* clean code

* clean up the code

* fix diff

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* add chat_template if exist

* clean up the code

* fix cpu-backend

* chore: whitespace trim fix + typo fix

* Fix: address review feedback

* restore `FREQ_BASE_SWA` constant

* Fix: address review feedback2

* Fix:typecheck

* Fix: address review feedback3

* final cleanup

---------

Co-authored-by: mmngays <146910567+mmngays@users.noreply.github.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-12-28 17:28:31 +01:00
Johannes Gäßler 026d2ad472 llama: fix magic number of 999 for GPU layers (#18266) 
* llama: fix magic number of 999 for GPU layers

* use strings for -ngl, -ngld

* enacapsulate n_gpu_layers, split_mode
 2025-12-27 20:18:35 +01:00
Xuan-Son Nguyen 4cbafad4f0 model: support MiMo-V2-Flash (#18328) 
* mimov2: convert ok

* rename mimov2 --> mimo2

* fix conversion

* runnable not incorrect

* use sink

* add_sliding_window_pattern

* add swa and per-layer n_head_kv

* correct params

* somewhat working

* correct gating func

* nits

* mimo2: wire RMS eps + MoE bias + converter guards

* add co-author

Co-authored-by: Aaryan-Kapoor <Aaryan-Kapoor@users.noreply.github.com>

* use add_rope_freq_base_swa

---------

Co-authored-by: Aaryan Kapoor <aaryankapoor2006@gmail.com>
Co-authored-by: Aaryan-Kapoor <Aaryan-Kapoor@users.noreply.github.com>
 2025-12-24 23:07:08 +01:00
Saba Fallah 54132f1b1f model : support for LlamaBidirectionalModel architecture (#18220) 
* model: llama-embed-nemotron

* minor: python lint

* changed arch-name

* templated llm_build_llama to be used for both llama and llama-embed arch
 2025-12-24 14:02:36 +01:00
Alessandro98-git 96e33a814e model : fix div-by-zero for Nemotron V2 (#18309) 
* llama-model : fix Nemotron V2 crash by moving MoE parameters calculation

* remove whitespace

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-12-23 03:04:57 +01:00
Ryan Mangeno dfc959b886 model : Granite Embedding support (#15641) 
ModernBERT but without `head.norm` so will currently fail to convert and run any other ModernBERT models, PRs with `head.norm` support welcome!

* constants and tensor mappings for modern bert support, model not supported yet but working on getting conversion to work for encoder only

* conversion now working, hf -> gguf

* working on support, now working on building graph

* some cleanup

* cleanup

* continuing

* correct tensor shape for qkv

* fixed tensor mappings and working on buildin graph

* tensor debugging now works -> (llama-eval-callback), instead of simulated gate split with views, GEGLU is now used which does exactly this

* cleanup

* cleanup

* cleanup

* more cleanup

* ubatch issues, the assert for checking equal seqs in llama-graph.cpp when building attention  keeps failing, setting ubatch size to 1 when running llama-embedding with --ubatch-size 1 makes it work, but needs to be looked into more

* added cls token per previous modern bert attempt, still working on checking out the rest

* fixed pre tokenizer and still working through previous pr

* working through previous attemp, implimented more accurate conversion per previous attempt, added local sliding window attention that alternates every third layer

* fixed pre tokenizer

* working on swa with local and global alternating attention

* some cleanup and now fails on build attn

* starting to work, and some cleanup, currently failing on last layer construction in graph build

* alternating rope implemented and modern bert graph build succeeds

* fixed asser for equal ubatch seq

* cleanup

* added mask check in vocab

* fixed alternating rope, the hparams.rope_freq_base_train and hparams.rope_freq_base_train_swa were the same and i set them to correct values

* reuse variable

* removed repeat

* standard swa method can be used instead of a new enum being LLAMA_SWA_TYPE_LOCAL

* correct swa layer indexing, is supposed to be 0, 3, 6 ... instead of 1, 4, 7 ...

* more modular hparam setting

* replaced attn out norm with ffn_norm and cosine similarity between hf embds and llama.cpp embds went way up, from 0.05 to 0.24, replaced the cacheless kv with swa todo per the previous conversion

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update convert_hf_to_gguf_update.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-vocab.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-graph.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-arch.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* removed redundant hparam set

* enums for model sizes

* conversion for modern-bert model supported rather than just granite-small

* Update src/llama-model.cpp

Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Update src/llama-model.cpp

Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* fixed ordering of enum for freq_base_swa

* fixed where I added residual, now gives much much better embeddings~

* readded cacheless logic

* removing whitespace

* conversion now working for swa pattern - dense every n layers

* modern bert put into seperate src file

* removing whitespace

* fixed whitespace and newline errors in editorconfig job

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* better naming convention, n_swa_pattern -> swa_period

* reusing sliding_window_pattern key rather than making new dense_every_n_layers key, and adding writing and reading support

* fixing pyright type-check fail

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/gguf_writer.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-hparams.h

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model-saver.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/models/modern-bert.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/models/modern-bert.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/models/modern-bert.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/gguf_writer.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/models/modern-bert.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/models/modern-bert.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model-loader.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model-loader.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model-loader.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* added descriptions in llama-model

* fixed tensor mappings for conversion

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* mapping name for size

* nits

* unused

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
 2025-12-23 00:28:19 +01:00
Johannes Gäßler 57c1e05643 llama: offload output layer to GPU first (#18148) 2025-12-18 08:12:18 +01:00
Xuan-Son Nguyen ef83fb8601 model: fix LFM2 missing tensors (#18105) 2025-12-16 19:07:43 +01:00
Xuan-Son Nguyen 3d86c6c2b5 model: support GLM4V vision encoder (#18042) 
* convert ok

* no deepstack

* less new tensors

* cgraph ok

* add mrope for text model

* faster patch merger

* add GGML_ROPE_TYPE_MRNORM

* add support for metal

* move glm4v do dedicated graph

* convert: add norm_embd

* clip: add debugging fn

* working correctly

* fix style

* use bicubic

* fix mrope metal

* improve cpu

* convert to neox ordering on conversion

* revert backend changes

* force stop if using old weight

* support moe variant

* fix conversion

* fix convert (2)

* Update tools/mtmd/clip-graph.h

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* process mrope_section on TextModel base class

* resolve conflict merge

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-12-16 11:25:26 +01:00
Daniel Bevenius 2995341730 llama : add support for NVIDIA Nemotron 3 Nano (#18058) 
* llama : add support for NVIDIA Nemotron Nano 3

This commit adds support for the NVIDIA Nemotron Nano 3 model, enabling
the conversion and running of this model.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-12-16 07:19:26 +01:00
HelloKS 9d52f17ae3 model : add KORMo model (#18032) 
* vocab: add KORMo Tokenizer

* model: add KORMoForCausalLM

* vocab: change pretokenizer to qwen2

* lint: fix unintended line removal

* model: make qwen2 bias tensor optional

* model: use qwen2 architecture for KORMo
 2025-12-15 18:51:43 +01:00
Johannes Gäßler b1f3a6e5db llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653) 
* llama: automatically fit args to free memory

llama-fit-params tool

* fix CI

* hints for bug reports, ensure no reallocation

* fix segfault with Vulkan

* add llama-fit-params to CI

* fix CI

* fix CI

* fix CI

* minor adjustments

* fix assignment of 1 dense layer

* fix logger not being reset on model load failure

* remove --n-gpu-layer hint on model load failure

* fix llama-fit-params verbosity

* fix edge case

* fix typo [no ci]
 2025-12-15 09:24:59 +01:00
Xuan-Son Nguyen 0759b09c90 graph: add f_attn_temp_offset (#18025) 2025-12-14 13:05:59 +01:00
Georgi Gerganov 609a2d0268 models : fix YaRN regression + consolidate logic (#18006) 
* models : fix YaRN regression + consolidate logic

* cont : fix the fix

* cont : remove header

* cont : add header
 2025-12-14 08:34:56 +02:00
Georgi Gerganov 7bed317f53 models : fix the attn_factor for mistral3 graphs + improve consistency (#17945) 
* models : fix the attn_factor for mistral3 graphs

* cont : rework attn_factor correction logic

* cont : make deepseek2 consistent

* cont : add TODO

* cont : special-case DSv2

* cont : revert Mistral 3 Large changes

* cont : fix DS2 to use the original attn_factor

* cont : minor comments
 2025-12-12 17:12:40 +02:00
Eric Zhang b677721819 model : Qwen3-Next-80B-A3B has 48 layers (#17898) 
* model : Qwen3-Next-80B-A3B has 48 layers

* model : Add 80B-A3B type name
 2025-12-10 15:22:40 +01:00
Sigbjørn Skjæret 42b12b5608 model : nit, DeepSeek V1 MoE is 16B and GigaChat is 20B (#12652) 
* nit, DeepSeek V1 MoE is 16B

* base type on n_ff_exp instead
 2025-12-09 12:15:06 +01:00
philip-essential 1d2a1ab73d model : support Rnj-1 (#17811) 
* add support for rnj1

* refactor gemma3 to support rnj-1

* address review comments
 2025-12-09 04:49:03 +01:00
Xuan-Son Nguyen 4d3726278b model: add llama 4 scaling for mistral-large (deepseek arch) (#17744) 2025-12-07 22:29:54 +01:00
Herman Semenoff 37adc9c6ba ggml, llama : use defaulted constructors/destructors (#17649) 2025-12-03 07:12:18 +01:00
Piotr Wilkin (ilintar) 746f9ee889 Override SSM_A op for Qwen3 Next to reduce splits (#17587) 
* Override SSM_A op for Qwen3 Next to reduce splits

* New tensor mapping SSM_A_NOSCAN for SSM_A used outside of OP_SSM_SCAN context.

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-12-02 00:43:13 +01:00
Gilad S. 00c361fe53 fix: llama arch implementation (#17665) 2025-12-01 21:21:13 +01:00
Xuan-Son Nguyen cd3c118908 model: support Ministral3 (#17644) 
* conversion script

* support ministral 3

* maybe this is better?

* add TODO for rope_yarn_log_mul

* better ppl (tested on 14B-Instruct)

* Add Ministral3 support to Mistral format

* improve arch handling

* add sizes

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* nits

---------

Co-authored-by: Julien Denize <julien.denize@mistral.ai>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-12-01 12:26:52 +01:00
Piotr Wilkin (ilintar) ff55414c42 model : Qwen3 Next (#16095) 
* Qwen3 Next - cleaned up version

* Whitespaces and stuff

* Correct minor errors

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Misc. fixes.

* Clean up code, add missing hybrid qualifier

* Did someone transpose the SOLVE_TRI result matrix? Perhaps...

* Whitespace

* Proper tensors for cb calls

* Use llama-graph.h vertical alignment

* BROKEN: chunking

* Set new tensors as inputs.

* Proper chunk logic

* It's the circle of life...

* More shenanigans for n_seq > 1

* Nail in the coffin?

* Fix Windows build

* Eh, one fails on Windows, the other fails on Mac... just use general capture.

* quant : cleanup

* model : cleanup

* qwen3 : cleanup

* cont : cleanup

* cont : cleanup

* ggml : revert change

* qwen3 : cleanup

* cont : cleanup

* Readd cmath

* qwen3 : fix typo

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Usual suspects

* fix my bad suggestion

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-11-28 12:02:56 +01:00
Georgi Gerganov 6783b11fb0 models : fix LFM2 tensors (#17548) 2025-11-27 16:04:29 +02:00
Aaron Teo 877566d512 llama: introduce support for model-embedded sampling parameters (#17120) 2025-11-25 09:56:07 +08:00
william pan 4902eebe33 models : Added support for RND1 Diffusion Language Model (#17433) 
* Converted RND1 model to GGUF weights

* RND1 llama.cpp support v1

* RND1 llama.cpp support v2 non causal bug

* RND1 llama.cpp support v3 doccumentation

* RND1 llama.cpp support v4 clean code

* linting issues

* RND1 pr fixes v1

* RND1 pr fixes v2

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Diffusion documentation edits

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-11-24 14:16:56 +08:00
ubergarm 23bc779a6e model : detect GigaChat3-10-A1.8B as deepseek lite (#17420) 
* Detect GigaChat3-10-A1.8B as deepseek lite

Hardcodes checking number of layers to detect if lite version of deepseek.

* Add commnent identifying deepseek lite variants

deepseek lite variants include DeepSeek-V2-Lite, GigaChat3-10B-A1.8B
 2025-11-21 14:51:38 +01:00
Bartowski e1fcf8b09b model : add AfmoeForCausalLM support (#16477) 
* Add AFMOE model support

* Update to vocab

* Add model sizing

* Undo Rope change for ARCEE model

* Address review comments

* Update modeling code is_sliding -> use_rope, replace hard-coded logic

* Fix AFMOE tokenizer

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update AFMoE tokenizer class identification to be more unique

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-11-14 13:54:10 +01:00
Sigbjørn Skjæret 9008027aa3 hparams : add n_embd_inp() to support extended embed (#16928) 
* add n_embd_full to support extended embed

* don't change output

* rename to n_embd_inp

* restore n_embd where applicable
 2025-11-07 19:27:58 +01:00
Li Pengzhan 9f052478c2 model : add openPangu-Embedded (#16941) 
* Model: add openPangu-Embedded

* fixed according to reviewer's comments

* fixed the chat template check condition

* Apply suggestions from code review

change the chat-template check condition and some formatting issue

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* whitespace cleanup

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-11-05 10:28:58 +01:00
Georgi Gerganov cd5e3b5754 server : support unified cache across slots (#16736) 
* server : support unified context across slots

* cont : fix speculative decoding initialization

* context : fix n_ctx_per_seq computation

* server : purge slots one by one

* tests : add unified cache server tests

* llama : update per-seq context computation

* test-thread-safety : handle tiny training context of the input model

* server : fix server_tokens clear()

* server : use 4 slots + unified KV by default

* llama : add note about context size queries

* cont : update todos [no ci]

* context : do not cap the size of the context

* tests : adjust parameters to be CI friendlier

* context : add warning
 2025-11-02 18:14:04 +02:00
Piotr Wilkin (ilintar) bea04522ff refactor : llama-model.cpp (#16252) 
* Sqashed: llama-model.cpp refactoring

* Fix formatting of attn / ffn / ffn_moe calls

* Fix import regression / unify spacing in models.h

* totally DID NOT miss those!

* Add missing qwen3vl(moe) models

* Add missing new .cpp files to build

* Remove extra semicolons

* Editor checker

* Update src/models/models.h

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-10-31 23:40:23 +01:00
Piotr Wilkin (ilintar) 0de0a01576 model : Minimax M2 (#16831) 
* Model: Minimax M2

* Cleanup

* Cleanup pt. 2

* Cleanup pt. 3

* Update convert_hf_to_gguf_update.py - merge catch blocks

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Remove vocab models and test

* Remove all redundant hparam settings covered by TextModel

* Move super to start, don't set block_count

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/constants.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-10-31 21:20:47 +01:00
Giuseppe Scrivano e58d585604 model : add Granite Hybrid nano types (#16896) 
Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
 2025-10-31 21:20:07 +01:00
JJJYmmm d261223d24 model: add support for qwen3vl series (#16780) 
* support qwen3vl series.

Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>

* bugfix: fix the arch check for qwen3vl-moe.

* use build_ffn

* optimize deepstack structure

* optimize deepstack feature saving

* Revert "optimize deepstack feature saving" for temporal fix

This reverts commit f321b9fdf1.

* code clean

* use fused qkv in clip

* clean up / rm is_deepstack_layers for simplification

* add test model

* move test model to "big" section

* fix imrope check

* remove trailing whitespace

* fix rope fail

* metal : add imrope support

* add imrope support for sycl

* vulkan: add imrope w/o check

* fix vulkan

* webgpu: add imrope w/o check

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix tensor mapping

---------

Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-10-30 16:19:14 +01:00
Tianyue-Zhao bacddc049a model: Add support for CogVLM model (#15002) 
* Added GGUF mappings for CogVLM model

* Add tensor mapping for CogVLM visual encoder

* Add CogVLM to conversion script, no vision part yet

* Added CogVLM vision model to conversion script

* Add graph for CogVLM CLIP model

* Add graph for CogVLM

* Fixes for CogVLM. Now compiles.

* Model now runs

* Fixes for cogvlm graph

* Account for graph context change after rebase

* Changes for whitespace

* Changes in convert script according to comments

* Switch CogVLM LLM graph to merged QKV tensor

* Use rope_type variable instead of direct definition

* Change CogVLM CLIP encoder to use SWIGLU

* Switch CogVLM CLIP to use merged QKV

* Apply rebase edits and remove ggml_cont call that is now unnecessary

* clean up

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
 2025-10-30 12:18:50 +01:00
Georgi Gerganov 85a7d8677b memory : remove KV cache size padding (#16812) 
* memory : remove KV cache size padding

* cont : restore padding for n_kv tensor shape

* server : use slot context size instead of training context size

* server : simplify context limit logic
 2025-10-28 20:19:44 +02:00
Johannes Gäßler 7a0e900e36 llama: consistent ctx <-> buf order for KV cache (#16746) 2025-10-28 11:23:54 +01:00
Johannes Gäßler 945501f5ea llama: fix leaked buffers for mmap + split files (#16765) 2025-10-27 09:17:31 +01:00