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
7,853 Commits 609 Branches 6,697 Tags
b7853
Commit Graph

100 Commits

Author SHA1 Message Date
Georgi Gerganov 8f80d1b254 graph : fix nkvo offload with FA (#19105) 2026-01-26 20:18:34 +02:00
Georgi Gerganov d9c6ce46f7 kv-cache : support V-less cache (#19067) 
* kv-cache : support V-less cache

* cuda : better check for V_is_K_view

* cuda : improve V_is_K_view check

* graph : add comments

* hparams : refactor
 2026-01-25 15:48:56 +02:00
Georgi Gerganov 557515be1e graph : utilize ggml_build_forward_select() to avoid reallocations (#18898) 
* graph : avoid branches between embedding and token inputs

* models : make deepstack graphs (e.g. Qwen3 VL) have constant topology

* ci : enable -DGGML_SCHED_NO_REALLOC=ON for server CI

* cont : pad token embeddings to n_embd_inp
 2026-01-23 18:22:34 +02:00
Georgi Gerganov a5eaa1d6a3 mla : make the V tensor a view of K (#18986) 
* mla : pass V as a view of K to the FA op

* cuda : adjust mla logic to new layout

* kv-cache : fix rope shift

* tests : remove comment

* cuda : fix reusable_cutoff

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

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
 2026-01-22 22:09:01 +02:00
Tarek Dakhran ad8d85bd94 memory : add llama_memory_hybrid_iswa (#18601) 
* memory : add llama_memory_hybrid_iswa

* Update src/llama-memory-hybrid-iswa.cpp

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

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2026-01-21 14:30:23 +02:00
Gabe Goodhart 076b0faf7d graph : clean up t5 input builders (#18795) 
* fix: Remove unnecessary `h` loops where `h` was only ever 0

Branch: CleanUpT5InputBuilders

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Remove unnecessary padding loop that is never hit anymore

The upper bound used to use GGML_PAD(n_tokens, GGML_KQ_MASK_PAD), but was
removed in https://github.com/ggml-org/llama.cpp/pull/17910 leaving the
loop dead.

Branch: CleanUpT5InputBuilders

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
 2026-01-13 09:43:51 +01:00
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
Georgi Gerganov 2da64a2f8a models : fix backend assignment for Granite/Nemotron graphs (#18599) 
* models : fix backend assignment for Granite/Nemotron graphs

* cont : add ref

* cont : move call to build_inp_embd()
 2026-01-05 12:34:23 +02:00
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
Georgi Gerganov c69c7ebc90 graph : fix graph reuse logic when n_pos_per_embd > 1 (#18566) 2026-01-03 23:59:06 +02:00
Georgi Gerganov c560316440 graph : reuse SSM graphs (#16490) 
* graph : reuse hybrid graphs

* graph : reuse recurrent graphs

* graph : fix reuse check for recurrent inputs

* memory : move the recurrent state into the memory context

* Revert "memory : move the recurrent state into the memory context"

This reverts commit 00f115fe810815d4a22a6dee0acc346131e970e1.

* cont : fix build
 2025-12-16 09:36:21 +02:00
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
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
Georgi Gerganov 4dff236a52 ggml : remove GGML_KQ_MASK_PAD constant (#17910) 
* ggml : remove GGML_KQ_MASK_PAD constant

* cont : remove comment
 2025-12-10 20:53:16 +02:00
Sigbjørn Skjæret c8554b66e0 graph : use fill instead of scale_bias in grouped expert selection (#17867) 
* use fill instead of scale_bias in grouped expert selection

* do not explicitly use _inplace
 2025-12-08 21:29:59 +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
Aman Gupta 6eea666912 llama-graph: avoid expand_forward for fusion (#17633) 2025-12-01 11:12:48 +02:00
Georgi Gerganov 583cb83416 ggml : add ggml_top_k (#17365) 
* ggml : add ggml_top_k

* cont : add ggml_argsort_top_k

* metal : add top_k support

* ggml : cleanup

* tests : add virtual err() function for test_case

* ggml : add comments
 2025-11-25 15:31:43 +02:00
Aman Gupta a90eb94ca9 CUDA: fuse rope + set_rows (#16884) 
* CUDA: add fused rope

* move k forward_expand up

* create helper function instead of re-using params

* make assert statement more in line with comment

* rope_norm: coalesced writes to global mem
 2025-11-13 08:50:01 +08:00
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
Jan Boon d7395115ba llama : use std::abs instead of abs (#16853) 2025-10-30 08:30:58 +02:00
Sigbjørn Skjæret f696428ce8 graph : add clamping to ffn_moe_weights_sum to avoid div-by-zero (#16655) 
* add missing norm topk bias

* use clamping instead, update number and add comment
 2025-10-26 17:20:32 +01:00
Aman Gupta f77c13b91f CUDA: General GEMV fusion (#16715) 2025-10-26 19:28:04 +08:00
Sigbjørn Skjæret 84bf3c6778 model : add BailingMoeV2 support (#16063) 
* add BailingMoeV2 support

* update llm types

* undo

* undo

* update llm types

* add model collection link

* update

* almost working

* correct group selection and rename n_group_exp

* avoid large top_k and use argmax instead for now

if we had something like argmax2 that would be equivalent, but this works fine until then

* poke

* skip group selection when there are no tokens

* fix 1T conversion

* hopefully fixed expert group selection

third time's the charm?

* make expert group selection generally available

The new LLaDA2Moe model uses this method too, make it generally available regardless of architecture.

* allow n_expert_groups to be 1 (Kimi K2)

* address review suggestions
 2025-10-20 21:38:20 +02:00
Georgi Gerganov e60f241eac metal : FA support F32 K and V and head size = 32 (#16531) 
* metal : FA support F32 K and V and head size = 32

* graph : remove obsolete comment [no ci]
 2025-10-13 23:07:57 +03:00
Georgi Gerganov e38b7c6e9e graph : support cacheless embeddings with FA and iSWA (#16528) 
* graph : support cacheless embeddings with FA and iSWA

* cont : deduplicate mask creation

* cont : fix name
 2025-10-13 22:42:37 +03:00
Saba Fallah e08db42595 model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367) 
* model: EmbeddingGemma sentence-transformers dense linear projections support

* model: add support for EmbeddingGemma SentenceTransformers dense linear projections

Adding support for the Dense modules used in EmbeddingGemma models.
EmbeddingGemma is a SentenceTransformers model with additional modules beyond the base Transformer backbone.

See: https://developers.googleblog.com/en/gemma-explained-embeddinggemma-architecture-and-recipe/

* model: add support for EmbeddingGemma SentenceTransformers dense linear projections

- converting model with dense-layers is optional
- introduced dense config params

* Update convert_hf_to_gguf.py

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* fixed formatting issues

* Update src/llama-graph.cpp

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

* - removed pooling_type_opt, always allow overriding pooling_type
- asserts checking dense features dims

* fix python lint

* fix ubuntu gcc build warning

* - fixed thread-safety test
- moved asserts to load_hparams

* - tidying up code
- simplifying graph-context expecting both dense weights

* minor : add TODO

---------

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-10-09 09:39:18 +03:00
Sigbjørn Skjæret 835b2b915c model : add GroveMoE support (#15510) 
* add GroveMoE support

* remove constexpr that fails on certain compilers

* revert crude scalar div implementation, use cast

* build_attn_inp_kv_unified -> build_attn_inp_kv

* fix build_attn

* re-apply ffn_exps regex changes
 2025-09-25 19:50:28 +02:00
Aman Gupta 077c94d0ca CUDA: add a fused top-K MoE kernel (#16130) 
* CUDA: add a fused top-K MoE kernel

This kernel does the following:
1. softmax over the logits per token [n_experts, n_tokens]
2. argmax reduce over the top-k (n_experts_used) logits
3. write weights + ids to global memory

It is intended as fusion of softmax->top-k->get_rows pipeline for MoE models

* Refactor into ggml_cuda_should_use_topk_moe

* Review: Use better coalescing pattern, use WARP_SIZE, store logits into registers before

* Review: format + micro-optimizations

* Fix bug: fix tie breakers

* Add optional norm + clean-up code

* Use smem for final write

* Add bounds check

* Use better memory pattern for writeback
 2025-09-25 16:35:05 +02:00
Douglas Hanley b5bd037832 llama : add support for qwen3 reranker (#15824) 2025-09-25 11:53:09 +03:00
Sigbjørn Skjæret b8e09f08b9 model : add grok-2 support (#15539) 
* add grok-2 support

* type fix

* type fix

* type fix

* "fix" vocab for invalid sequences

* fix expert tensor mapping and spaces in vocab

* add chat template

* fix norm tensor mapping

* rename layer_out_norm to ffn_post_norm

* ensure ffn_post_norm is mapped

* fix experts merging

* remove erroneous FFN_GATE entry

* concatenate split tensors and add more metadata

* process all expert layers and try cat instead of hstack

* add support for community BPE vocab

* fix expert feed forward length and ffn_down concat

* commit this too

* add ffn_up/gate/down, unsure if sequence is right

* add ffn_gate/down/up to tensor names

* correct residual moe (still not working)

* mess--

* fix embedding scale being applied twice

* add built in chat template

* change beta fast for grok if default value

* remove spm vocab in favor of community bpe vocab

* change attention temp length metadata type to integer

* update attention temp length metadata

* remove comment

* replace M_SQRT2 with std::sqrt(2)

* add yarn metadata, move defaults to hparams
 2025-09-14 23:00:59 +02:00
Sigbjørn Skjæret 6ab397e12b graph : support non-contiguous Q in build_attn_mha (#15908) 
* support non-contiguous Q in build_attn_mha

* Update src/llama-graph.cpp

ggml-ci

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

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-09-10 19:08:59 +02:00
Georgi Gerganov 663027fd54 context : fix n_outputs during reserve (#15858) 
ggml-ci
 2025-09-08 10:26:36 +03:00
Georgi Gerganov c610b6c11b kv-cache : fix SWA checks + disable cacheless iSWA (#15811) 
ggml-ci
 2025-09-05 10:39:22 +03:00
Daniel Bevenius fb15d649ed llama : add support for EmbeddingGemma 300m (#15798) 
This commit add support for the EmbeddingGemma 300m. This model supports
sliding window attention (SWA) and a new swq_type is introduced to
support symmetric SWA masking.

This commit also extracts the code from the function
llama_is_masked_swa in llama-impl.h, so that the logic can be shared
by both llm_graph_input_attn_no_cache::set_input and
llama_kv_cache::set_input_kq_mask.

With this commit the EmbeddingGemma 300m model can be converted to
to GGUF and used with llama.cpp.

Once the model has been uploaded to HuggingFace it can be used like
this:
```console
./build/bin/llama-cli -hf ggml-org/embeddinggemma-300m-GGUF:Q8_0
```
 2025-09-04 18:10:29 +02:00
Johannes Gäßler e81b8e4b7f llama: use FA + max. GPU layers by default (#15434) 
* llama: use max. GPU layers by default, auto -fa

* ggml-backend: abort instead of segfault
 2025-08-30 16:32:10 +02:00
Georgi Gerganov 8a4280ce43 kv-cache : remove LLAMA_SET_ROWS checks (#15505) 
ggml-ci
 2025-08-28 12:27:02 +03:00
Georgi Gerganov 0373486dbc graph : fix assert in memory-less build_attn (#15590) 
ggml-ci
 2025-08-26 17:45:17 +03:00
Georgi Gerganov 3f196be84b graph : remove build_attn_with_sinks overload (#15469) 
ggml-ci
 2025-08-21 18:44:45 +03:00
Georgi Gerganov 715a6db02c kv-cache : drop the "unified" prefix (#15467) 
* kv-cache : drop the "unified" prefix

ggml-ci

* cont : fix comment [no ci]
 2025-08-21 17:00:33 +03:00
Georgi Gerganov fd1234cb46 llama : add gpt-oss (#15091) 
* oai moe

* compat with new checkpoint

* add attn sink impl

* add rope scaling yarn

* logits match with latest transformers code

* wip chat template

* rm trailing space

* use ggml_scale_bias

* rm redundant is_swa_all

* convert interleaved gate_up

* graph : fix activation function to match reference (#7)

* vocab : handle o200k_harmony special tokens

* ggml : add attention sinks support (#1)

* llama : add attn sinks

* ggml : add attn sinks

* cuda : add attn sinks

* vulkan : add support for sinks in softmax

remove unnecessary return

* ggml : add fused swiglu_oai op (#11)

* ggml : add fused swiglu_oai op

* Update ggml/src/ggml-cpu/ops.cpp

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

* update CUDA impl

* cont : metal impl

* add vulkan impl

* test-backend-ops : more test cases, clean up

* llama : remove unfused impl

* remove extra lines

---------

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

---------

Co-authored-by: slaren <slarengh@gmail.com>

* repack mxfp4 upon conversion

* clean up a bit

* enable thinking

* add quick hack to render only some special tokens

* fix bf16 conversion

* remove vocab hack

* webui ok

* support chat parsing for gpt-oss

* fix webui

* direct mapping mxfp4, FINALLY

* force using mxfp4

* properly use lazy tensor

* ggml : add mxfp4

ggml : use e8m0 conversion instead of powf

Co-authored-by: Diego Devesa <slarengh@gmail.com>

change kvalues_mxfp4 table to match e2m1 (#6)

metal : remove quantization for now (not used)

cuda : fix disabled CUDA graphs due to ffn moe bias

vulkan : add support for mxfp4

cont : add cm2 dequant

* ggml : add ggml_add_id (#13)

* ggml : add ggml_add_id

* add cuda impl

* llama : add weight support check for add_id

* perf opt

* add vulkan impl

* rename cuda files

* add metal impl

* allow in-place ggml_add_id

* llama : keep biases on CPU with --cpu-moe

* llama : fix compile error

ggml-ci

* cuda : add fallback for __nv_cvt_e8m0_to_bf16raw

ggml-ci

* cleanup

ggml-ci

* sycl : fix supports_op for MXFP4

ggml-ci

* fix Unknown reasoning format

* ggml-cpu : fix AVX build

ggml-ci

* fix hip build

ggml-ci

* cuda : add mxfp4 dequantization support for cuBLAS

ggml-ci

* ggml-cpu : fix mxfp4 fallback definitions for some architectures

ggml-ci

* cuda : fix version required for __nv_cvt_e8m0_to_bf16raw

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: slaren <slarengh@gmail.com>
 2025-08-05 22:10:36 +03:00
Sam ef0144c087 model: support GLM 4.5 family of models (#14939) 
* model: Add GLM 4.5 (#14921)

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

* Merge in PR suggestions

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

* model: Add GLM 4.5 family of models (#14921)

1. Updated tensor_mapping.py with NextN tensor mappings

- Added proper tensor mappings for all NextN/MTP tensors in /Users/samm/git/llama.cpp/gguf-py/gguf/tensor_mapping.py
- Added mappings for: eh_proj, embed_tokens, enorm, hnorm, shared_head.head, shared_head.norm

2. Added num_nextn_predict_layers configuration

- Added LLM_KV_NUM_NEXTN_PREDICT_LAYERS constant to llama-arch.h and llama-arch.cpp
- Added num_nextn_predict_layers field to llama_hparams struct
- Updated GLM4_MOE parameter loading in llama-model.cpp to read this parameter
- Modified tensor loading logic to conditionally load NextN tensors based on num_nextn_predict_layers
- Added GGUF writer support in gguf_writer.py with add_num_nextn_predict_layers() method
- Updated conversion script to extract and write this parameter from HuggingFace config

3. Added FIM tokens for GLM4_MOE

- Added GLM-4.5's FIM tokens to llama-vocab.cpp:
  - <|code_prefix|> for FIM_PRE
  - <|code_suffix|> for FIM_SUF
  - <|code_middle|> for FIM_MID

4. Removed manual NextN tensor handling

- Removed the special-case handling in convert_hf_to_gguf.py that manually mapped NextN tensors
- NextN tensors are now handled automatically through the proper tensor mapping system

* glm 4.5 update tensors names

* model: glm 4.5 apply suggestions from code review

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

* Update src/llama-model.cpp

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

* model: glm 4.5 apply suggestions from code review

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

* model: glm 4.5 apply suggestions from code review

* Apply suggestions from code review

* patch broken chat template

* typings fix

* add TENSOR_SKIP flag


Co-authored-by: Diego Devesa <slarengh@gmail.com>

* Update src/llama-model-loader.h

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
 2025-08-04 20:29:25 +02:00
Dongliang Wei c1dacaa99b llama : merge build_moe_ffn_from_probs function into build_moe_ffn (#14968) 2025-07-31 14:12:20 +02:00
compilade 66625a59a5 graph : reduce splits for recurrent and hybrid models (#14825) 
* graph : avoid creating redundant s_copy views

* graph : comment the s_copy views
 2025-07-31 08:02:46 +03:00
Douglas Hanley a118d80233 embeddings: fix extraction of CLS pooling results (#14927) 
* embeddings: fix extraction of CLS pooling results

* merge RANK pooling into CLS case for inputs
 2025-07-30 08:25:05 +03:00
Dongliang Wei 6c6e397aff model : add support for SmallThinker series (#14898) 
* support smallthinker

* support 20b softmax, 4b no sliding window

* new build_moe_ffn_from_probs, and can run 4b

* fix 4b rope bug

* fix python type check

* remove is_moe judge

* remove set_dense_start_swa_pattern function and modify set_swa_pattern function

* trim trailing whitespace

* remove get_vocab_base of SmallThinkerModel in convert_hf_to_gguf.py

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

* better whitespace

Apply suggestions from code review

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

* use GGML_ASSERT for expert count validation

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

* Improve null pointer check for probs

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

* use template parameter for SWA attention logic

* better whitespace

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

* move the creation of inp_out_ids before the layer loop

* remove redundant judge for probs

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-07-28 13:47:00 +02:00
Georgi Gerganov bf9087f59a metal : fuse add, mul + add tests (#14596) 
ggml-ci
 2025-07-18 20:37:26 +03:00
Georgi Gerganov 9fb1042ce6 graph : fix graph reuse reset of params (#14760) 
ggml-ci
 2025-07-18 20:08:33 +03:00