309 Commits

Author	SHA1	Message	Date
Radoslav Gerganov	bcf7546160	server : add arg for disabling prompt caching (#18776) ... * server : add arg for disabling prompt caching Disabling prompt caching is useful for clients who are restricted to sending only OpenAI-compat requests and want deterministic responses. * address review comments * address review comments	2026-01-12 19:21:34 +02:00
Xuan-Son Nguyen	ce3bf9b1a4	server: update docs for sleeping [no ci] (#18777)	2026-01-12 13:01:24 +01:00
Georgi Gerganov	f307926482	server : adjust unified KV cache tests (#18716)	2026-01-10 17:51:56 +02:00
Xuan-Son Nguyen	9ac2693a30	server: fix n_cmpl not skipping processing prompt (#18663) ... * server: fix n_cmpl not skipping processing * fix infinite loop on empty batch * cont : init child samplers + modify child logic * cont : cleanup * cont : improve n_cmpl logic - launch the parent task first so it finds the slot with best cache - parent task waits for child tasks to be launched - when a child task finishes - remove its cache * cont : remove redundant function * cont : reduce parent checks * fix : nullptr task dereference --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2026-01-10 00:00:41 +01:00
Pascal	ec8fd7876b	Webui/file upload (#18694) ... * webui: fix restrictive file type validation * webui: simplify file processing logic * chore: update webui build output * webui: remove file picker extension whitelist (1/2) * webui: remove file picker extension whitelist (2/2) * chore: update webui build output * refactor: Cleanup * chore: update webui build output * fix: update ChatForm storybook test after removing accept attribute * chore: update webui build output * refactor: more cleanup * chore: update webui build output	2026-01-09 16:45:32 +01:00
Georgi Gerganov	53eb9435da	server : fix timing of prompt/generation (#18713)	2026-01-09 12:59:50 +02:00
Georgi Gerganov	f5f8812f7c	server : use different seeds for child completions (#18700) ... * server : use different seeds for child completions * cont : handle default seed * cont : note	2026-01-09 09:33:50 +02:00
Adrien Gallouët	55abc39355	vendor : update cpp-httplib to 0.30.0 (#18660) ... * vendor : update cpp-httplib to 0.30.0 * common : allow custom headers when downloading	2026-01-08 13:53:54 +01:00
R	3d26a09dc7	server : add thinking content blocks to Anthropic Messages API (#18551) ... * server : add thinking content blocks to Anthropic Messages API Add support for returning reasoning/thinking content in Anthropic API responses when using models with --reasoning-format deepseek and the thinking parameter enabled. - Non-streaming: adds thinking block before text in content array - Streaming: emits thinking_delta events with correct block indices - Partial streaming: tracks reasoning state across chunks via anthropic_has_reasoning member variable Tested with bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF model. * server : fix Anthropic API streaming for thinking content blocks Add signature field and fix duplicate content_block_start events in Anthropic Messages API streaming responses for reasoning models. * server: refactor Anthropic streaming state to avoid raw pointer Replace raw pointer to task_result_state with direct field copies: - Copy state fields in update() before processing chunk - Use local copies in to_json_anthropic() instead of dereferencing - Pre-compute state updates for next chunk in update() This makes the data flow clearer and avoids unsafe pointer patterns.	2026-01-06 16:17:13 +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
Vladislav Sayapin	da143b9940	server : fix router child env in containerized environments (#18562)	2026-01-05 14:12:05 +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
Anri Lombard	d5574c919c	webui: fix code copy stripping XML/HTML tags (#18518) ... * webui: fix code copy stripping XML/HTML tags * webui: update static build	2026-01-01 13:44:11 +01:00
Jeff Bolz	f14f4e421b	server: fix files built redundantly (#18474)	2025-12-30 13:11:13 +01:00
Xuan-Son Nguyen	51a48720b8	webui: fix prompt progress ETA calculation (#18468) ... * webui: fix prompt progress ETA calculation * handle case done === 0	2025-12-29 21:42:11 +01:00
Pascal	c9a3b40d65	Webui/prompt processing progress (#18300) ... * webui: display prompt preprocessing progress * webui: add percentage/ETA and exclude cached tokens from progress Address review feedback from ngxson * webui: add minutes and first chunk (0%) case * Update tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * Update tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * webui: address review feedback from allozaur * chore: update webui build output * webui: address review feedback from allozaur * nit * chore: update webui build output * feat: Enhance chat processing state * feat: Improve chat processing statistics UI * chore: update webui build output * feat: Add live generation statistics to processing state hook * feat: Persist prompt processing stats in hook for better UX * refactor: Enhance ChatMessageStatistics for live stream display * feat: Implement enhanced live chat statistics into assistant message * chore: update webui build output * fix: Proper tab for each stage of prompt processing/generation * chore: update webui build output * fix: Improved ETA calculation & display logic * chore: update webui build output * feat: Simplify logic & remove ETA from prompt progress * chore: update webui build output --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>	2025-12-29 19:32:21 +01:00
wbtek	5b1248c9af	server : Cmdline arg -to changes http read timeout from current 600sec default (#18279) ... * Prevent crash if TTFT >300sec, boosted to 90 days * server : allow configurable HTTP timeouts for child models * server : pass needed timeouts from params only --------- Co-authored-by: Greg Slocum <fromgit@wbtek.slocum.net>	2025-12-29 17:12:48 +01:00
Georgi Gerganov	2a85f720b8	server : handle closed connection for tasks (#18459)	2025-12-29 15:34:41 +02:00
o7si	4893cc07bb	server : fix crash when seq_rm fails for hybrid/recurrent models (#18391) ... * server : fix crash when seq_rm fails for hybrid/recurrent models * server : add allow_processing param to clear_slot	2025-12-26 16:35:29 +01:00
Xuan-Son Nguyen	f5acfb2ffa	server: (router) add stop-timeout option (#18350) ... * server: (router) add stop-timeout option * also allow stop while loading * add docs * unload_lru: also wait for unload to complete	2025-12-24 23:47:49 +01:00
Xuan-Son Nguyen	5ee4e43f26	server: return_progress to also report 0% processing state (#18305)	2025-12-23 21:49:05 +01:00
Pascal	5b6c9bc0f3	webui: apply webui_settings on first load (#18223) ... * webui: apply webui_settings on first load The webui_settings from /props were not applied on initial load when default_generation_settings.params was null Now syncs whenever serverProps is available, regardless of params, works for both single-model and router modes * chore: update webui build output	2025-12-23 15:48:03 +01:00
Xuan-Son Nguyen	849d021104	server: fix crash with model not having BOS/EOS (#18321)	2025-12-23 14:39:36 +01:00
Xuan-Son Nguyen	179fd82a72	gen-docs: automatically update markdown file (#18294) ... * gen-docs: automatically update markdown file * also strip whitespace * do not add extra newline * update TOC	2025-12-22 19:30:19 +01:00
Xuan-Son Nguyen	6ce863c803	server: prevent data race from HTTP threads (#18263) ... * server: prevent data race from HTTP threads * fix params * fix default_generation_settings * nits: make handle_completions_impl looks less strange * stricter const * fix GGML_ASSERT(idx < states.size()) * move index to be managed by server_response_reader * http: make sure req & res lifecycle are tied together * fix compile * fix index handling buggy * fix data race for lora endpoint * nits: fix shadow variable * nits: revert redundant changes * nits: correct naming for json_webui_settings	2025-12-22 14:23:34 +01:00
Xuan-Son Nguyen	3997c78e33	server: fix data race in to_json_anthropic (#18283)	2025-12-22 13:21:43 +01:00
Xuan-Son Nguyen	86af848153	server: (docs) remove mention about extra_args (#18262)	2025-12-22 12:22:01 +01:00
Xuan-Son Nguyen	ddcb75dd8a	server: add auto-sleep after N seconds of idle (#18228) ... * implement sleeping at queue level * implement server-context suspend * add test * add docs * optimization: add fast path * make sure to free llama_init * nits * fix use-after-free * allow /models to be accessed during sleeping, fix use-after-free * don't allow accessing /models during sleep, it is not thread-safe * fix data race on accessing props and model_meta * small clean up * trailing whitespace * rm outdated comments	2025-12-21 02:24:42 +01:00
Oleksandr Kuvshynov	408616adbd	server : [easy] fix per round speculative decode logging (#18211) ... Currently we always log 0, as we clear slot.drafted before. To reproduce: Run llama-server with devstral-2 as main model and devstral-2-small as md, and verbose logging: ``` % ./build/bin/llama-server -v \ -m ~/llms/Devstral-2-123B-Instruct-2512-UD-Q6_K_XL-00001-of-00003.gguf \ -md ~/llms/Devstral-Small-2-24B-Instruct-2512-UD-Q2_K_XL.gguf \ -c 8192 2> /tmp/llama.cpp.debug Check the log: slot update_slots: id 3 | task 0 | accepted 11/0 draft tokens, new n_tokens = 741 slot update_slots: id 3 | task 0 | accepted 4/0 draft tokens, new n_tokens = 746 slot update_slots: id 3 | task 0 | accepted 16/0 draft tokens, new n_tokens = 763 slot update_slots: id 3 | task 0 | accepted 11/0 draft tokens, new n_tokens = 775 slot update_slots: id 3 | task 0 | accepted 2/0 draft tokens, new n_tokens = 778 slot update_slots: id 3 | task 0 | accepted 4/0 draft tokens, new n_tokens = 783 slot update_slots: id 3 | task 0 | accepted 8/0 draft tokens, new n_tokens = 792 slot update_slots: id 3 | task 0 | accepted 2/0 draft tokens, new n_tokens = 795 slot update_slots: id 3 | task 0 | accepted 1/0 draft tokens, new n_tokens = 797 slot update_slots: id 3 | task 0 | accepted 1/0 draft tokens, new n_tokens = 799 slot update_slots: id 3 | task 0 | accepted 0/0 draft tokens, new n_tokens = 800 slot update_slots: id 3 | task 0 | accepted 2/0 draft tokens, new n_tokens = 803 slot update_slots: id 3 | task 0 | accepted 1/0 draft tokens, new n_tokens = 805 slot update_slots: id 3 | task 0 | accepted 6/0 draft tokens, new n_tokens = 812 slot update_slots: id 3 | task 0 | accepted 3/0 draft tokens, new n_tokens = 816 ``` After the fix, get correct per round logging: ``` slot update_slots: id 3 | task 0 | accepted 7/8 draft tokens, new n_tokens = 654 slot update_slots: id 3 | task 0 | accepted 1/2 draft tokens, new n_tokens = 656 slot update_slots: id 3 | task 0 | accepted 2/16 draft tokens, new n_tokens = 659 slot update_slots: id 3 | task 0 | accepted 1/16 draft tokens, new n_tokens = 661 slot update_slots: id 3 | task 0 | accepted 2/16 draft tokens, new n_tokens = 664 slot update_slots: id 3 | task 0 | accepted 16/16 draft tokens, new n_tokens = 681 slot update_slots: id 3 | task 0 | accepted 16/16 draft tokens, new n_tokens = 698 slot update_slots: id 3 | task 0 | accepted 3/4 draft tokens, new n_tokens = 702 slot update_slots: id 3 | task 0 | accepted 5/12 draft tokens, new n_tokens = 708 slot update_slots: id 3 | task 0 | accepted 16/16 draft tokens, new n_tokens = 725 slot update_slots: id 3 | task 0 | accepted 1/1 draft tokens, new n_tokens = 727 slot update_slots: id 3 | task 0 | accepted 8/16 draft tokens, new n_tokens = 736 ```	2025-12-20 10:57:40 +01:00
Xuan-Son Nguyen	9e39a1e6a9	server: support load model on startup, support preset-only options (#18206) ... * server: support autoload model, support preset-only options * add docs * load-on-startup * fix * Update common/arg.cpp Co-authored-by: Pascal <admin@serveurperso.com> --------- Co-authored-by: Pascal <admin@serveurperso.com>	2025-12-20 09:25:27 +01:00
Pascal	14931a826e	arg: fix order to use short form before long form (#18196) ... * arg: fix order to use short form before long form * arg: update doc * arg: update test-arg-parser * arg: address review feedback from ngxson simplified to check first.length() <= last.length() only fixed: --sampler-seq, --rerank, --draft ordering note: middle positions in 3+ arg sets are not verified * arg: update doc	2025-12-19 18:01:56 +01:00
Aman Gupta	cc0a04343e	server: friendlier error msg when ctx < input (#18174) ... * llama-server: friendlier error msg when ctx < input This PR adds formatted strings to the server's send_error function * llama-server: use string_format inline * fix test	2025-12-19 12:10:00 +01:00
Xuan-Son Nguyen	98c1c7a7bf	presets: refactor, allow cascade presets from different sources, add global section (#18169) ... * presets: refactor, allow cascade presets from different sources * update docs * fix neg arg handling * fix empty mmproj * also filter out server-controlled args before to_ini() * skip loading custom_models if not specified * fix unset_reserved_args * fix crash on windows	2025-12-19 12:08:20 +01:00
Aleksander Grygier	acb73d8340	webui: Add editing attachments in user messages (#18147) ... * feat: Enable editing attachments in user messages * feat: Improvements for data handling & UI * docs: Update Architecture diagrams * chore: update webui build output * refactor: Exports * chore: update webui build output * feat: Add handling paste for Chat Message Edit Form * chore: update webui build output * refactor: Cleanup * chore: update webui build output	2025-12-19 11:14:07 +01:00
Pascal	f9ec8858ed	webui: display prompt processing stats (#18146) ... * webui: display prompt processing stats * feat: Improve UI of Chat Message Statistics * chore: update webui build output * refactor: Post-review improvements * chore: update webui build output --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>	2025-12-18 17:55:03 +01:00
Aleksander Grygier	9ce64aed7d	webui: Fix selecting generated output issues during active streaming (#18091) ... * draft: incremental markdown rendering with stable blocks * refactor: Logic improvements * refactor: DRY Markdown post-processing logic * refactor: ID generation improvements * fix: Remove runes * refactor: Clean up & add JSDocs * chore: update webui static output * fix: Add tick to prevent race conditions for rendering Markdown blocks Suggestion from @ServeurpersoCom Co-authored-by: Pascal <admin@serveurperso.com> * chore: Run `npm audit fix` * chore: update webui static output * feat: Improve performance using global counter & id instead of UUID * refactor: Enhance Markdown rendering with link and code features * chore: update webui static output * fix: Code block content extraction * chore: update webui static output * chore: update webui static output --------- Co-authored-by: Pascal <admin@serveurperso.com>	2025-12-18 11:13:52 +01:00
Kim S.	900316da4e	webui: fix chat screen shadow width (#18010) ... * webui: fix chat screen shadow width * chore: add index.html.gz	2025-12-18 11:08:42 +01:00
Pascal	6ce3d85796	server: (webui) add --webui-config (#18028) ... * server/webui: add server-side WebUI config support Add CLI arguments --webui-config (inline JSON) and --webui-config-file (file path) to configure WebUI default settings from server side. Backend changes: - Parse JSON once in server_context::load_model() for performance - Cache parsed config in webui_settings member (zero overhead on /props) - Add proper error handling in router mode with try/catch - Expose webui_settings in /props endpoint for both router and child modes Frontend changes: - Add 14 configurable WebUI settings via parameter sync - Add tests for webui settings extraction - Fix subpath support with base path in API calls Addresses feedback from @ngxson and @ggerganov * server: address review feedback from ngxson * server: regenerate README with llama-gen-docs	2025-12-17 21:45:45 +01:00
Xuan-Son Nguyen	e85e9d7637	server: (router) disable SSL on child process (#18141)	2025-12-17 21:39:08 +01:00
Kim S.	d37fc93505	webui: fix chat header width when sidebar is closed (#17981) ... * webui: fix chat header width when sidebar is closed * chore: add index.html.gz	2025-12-17 20:05:45 +01:00
Xuan-Son Nguyen	bde461de8c	server: (router) allow child process to report status via stdout (#18110) ... * server: (router) allow child process to report status via stdout * apply suggestions	2025-12-17 14:54:11 +01:00
yifant-code	59977eba7b	server: fix crash when batch > ubatch with embeddings (#17912) ... * server: fix crash when batch > ubatch with embeddings (#12836) Fixes #12836 where the server crashes with GGML_ASSERT failure when running with embeddings enabled and n_batch > n_ubatch. Root cause: Embeddings use non-causal attention which requires all tokens to be processed within a single ubatch. When n_batch > n_ubatch, the server attempts to split processing, causing assertion failure. Solution: - Add parameter validation in main() after common_params_parse() - When embeddings enabled and n_batch > n_ubatch: * Log warnings explaining the issue * Automatically set n_batch = n_ubatch * Prevent server crash This follows the approach suggested by @ggerganov in issue #12836. Note: This supersedes stalled PR #12940 which attempted a runtime fix in the old examples/server/server.cpp location. This implementation validates at startup in tools/server/server.cpp (current location). Testing: - Build: Compiles successfully - Validation triggers: Warns when -b > -ub with --embedding - Auto-correction works: Adjusts n_batch = n_ubatch - No false positives: Valid params don't trigger warnings - Verified on macOS M3 Pro with embedding model * Update tools/server/server.cpp --------- Co-authored-by: ytian218 <ytian218@bloomberg.net> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2025-12-16 14:27:36 +02:00
Xuan-Son Nguyen	7b1db3d3b7	arg: clarify auto kvu/np being set on server (#17997) ... * arg: clarify auto kvu/np being set on server * improve docs * use invalid_argument	2025-12-16 12:01:27 +01:00
2114L3	5f5f9b4637	server: Update README.md incorrect argument (#18073) ... n-gpu-layer is incorrect argument is n-gpu-layers with the 's'	2025-12-16 11:50:43 +01:00
Aleksander Grygier	3034836d36	webui: Improve copy to clipboard with text attachments (#17969) ... * feat: Create copy/paste user message including "pasted text" attachments * chore: update webui build output * chore: update webui static output * fix: UI issues * chore: update webui static output * fix: Decode HTML entities using `DOMParser` * chore: update webui build output * chore: update webui static output	2025-12-16 07:38:46 +01:00
Aleksander Grygier	a20979d433	webui: Add setting to always show sidebar on Desktop (#17809) ... * feat: Add setting to always show Sidebar on Desktop * chore: update webui build output * feat: Add auto-show sidebar setting * fix: Mobile settings dialog UI * chore: update webui build output * feat: UI label update * chore: update webui build output * chore: update webui build output * chore: update webui build output * refactor: Cleanup * chore: update webui build output	2025-12-16 07:31:37 +01:00
Darius Lukas	40d9c394f4	Webui: Disable attachment button and model selector button when prompt textbox is disabled. (#17925) ... * Pass disabled state to the file attachments button and the model selector button. * Update index.html.gz * Fix model info card in non-router mode. * Update index.html.gz	2025-12-16 07:15:49 +01:00
Pascal	0f4f35e7be	Fix unreadable user markdown colors and truncate long texts in deletion dialogs (#17555) ... * webui: limit conversation name length in dialogs * webui: fix unreadable colors on links and table cell hover in user markdown * webui: keep table borders visible in user markdown * webui: updating unified exports * Update tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentThumbnailFile.svelte Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * chore: update webui build output * chore: update webui build output * chore: update webui build output --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>	2025-12-15 16:34:53 +01:00
Thomas Jarosch	e73d548659	webui: add "delete all conversations" button to import/export tab (#17444) ... * webui: add "delete all conversations" button to import/export tab - Add 'Delete all conversations' functionality with confirmation dialog - Add Trash icon and destructive styling for clear visual indication - Redirects to "?new_chat=true#/" by using conversationsStore.deleteAll() * chore: update webui build output	2025-12-15 11:29:29 +01:00
Georgi Gerganov	254098a279	common : refactor common_sampler + grammar logic changes (#17937) ... * common : refactor common_sampler + grammar logic changes * tests : increase max_tokens to get needed response * batched : fix uninitialized samplers	2025-12-14 10:11:13 +02:00