Kawrakow cde642e591 Grouped expert routing (CPU only) (#836) ...

* Better argsort (CPU)

* Attemt at grouped topk

* This seems to do the trick for grouped experts routing

* Cleanup

* Trying to merge, something is not right

* Working merged grouped top_k (CPU)

* Add command line option to enable grouped expert routing

* Add grouped expert routing option to llama-bench

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2025-10-16 14:57:02 +03:00

..

CMakeLists.txt

Enable and clean up compiler warnings in src (#824)

2025-10-11 16:01:13 +03:00

llama-arch.cpp

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

2025-10-15 14:20:40 +03:00

llama-arch.h

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

2025-10-15 14:20:40 +03:00

llama-build-context.cpp

Grouped expert routing (CPU only) (#836)

2025-10-16 14:57:02 +03:00

llama-build-context.h

Grouped expert routing (CPU only) (#836)

2025-10-16 14:57:02 +03:00

llama-context.h

Refactor file llama.cpp (#823)

2025-10-11 11:35:20 +03:00

llama-cparams.h

Grouped expert routing (CPU only) (#836)

2025-10-16 14:57:02 +03:00

llama-grammar.cpp

Tool calls support from mainline (#723)

2025-09-01 08:38:49 +03:00

llama-grammar.h

Tool calls support from mainline (#723)

2025-09-01 08:38:49 +03:00

llama-hparams.cpp

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

2025-10-15 14:20:40 +03:00

llama-hparams.h

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

2025-10-15 14:20:40 +03:00

llama-impl.h

Remove double definition of LLAMA_LOG_DEBUG

2025-09-01 08:42:04 +03:00

llama-load-tensors.cpp

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

2025-10-15 14:20:40 +03:00

llama-mmap.cpp

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00

llama-mmap.h

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00

llama-model-loader.cpp

Refactor file llama.cpp (#823)

2025-10-11 11:35:20 +03:00

llama-model-loader.h

Refactor file llama.cpp (#823)

2025-10-11 11:35:20 +03:00

llama-model.cpp

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

2025-10-15 14:20:40 +03:00

llama-model.h

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

2025-10-15 14:20:40 +03:00

llama-quantize.cpp

Fix PATH_MAX not defined on Windows (#828)

2025-10-13 09:25:57 +03:00

llama-sampling.cpp

Enable and clean up compiler warnings in src (#824)

2025-10-11 16:01:13 +03:00

llama-sampling.h

add dry sampler (#513)

2025-06-19 10:24:53 +03:00

llama-vocab.cpp

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

2025-10-15 14:20:40 +03:00

llama-vocab.h

model : add grok-2 support (#782)

2025-09-23 16:31:01 +02:00

llama.cpp

Grouped expert routing (CPU only) (#836)

2025-10-16 14:57:02 +03:00

unicode-data.cpp

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

unicode-data.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

unicode.cpp

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00

unicode.h

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00