ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
53fb7a4118520d4cccc9cab4f770dd6b4532604f
ik_llama.cpp/src
History
Kawrakow f65fefa36c Slightly faster TG for split mode "graph" (#1057) 
* Rearrange graph nodes

So that we can do graph portions that are the same on 2 or more
GPUs at the same time.

* Separate graph compute implementation for split mode graph

* This is better

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-12-12 07:54:37 +01:00
..
CMakeLists.txt
Enable and clean up compiler warnings in src (#824)
2025-10-11 16:01:13 +03:00
llama-arch.cpp
Adding ministral3: this seems to work (#1030)
2025-12-03 11:01:21 +01:00
llama-arch.h
Adding ministral3: this seems to work (#1030)
2025-12-03 11:01:21 +01:00
llama-build-context.cpp
Slightly faster TG for split mode "graph" (#1057)
2025-12-12 07:54:37 +01:00
llama-build-context.h
Hadamard transforms for K-cache - CPU only (#1033)
2025-12-04 06:51:11 +01:00
llama-context.h
POC: CUDA tensor parallel (MoE models) (#1022)
2025-12-01 19:25:40 +01:00
llama-cparams.h
Hadamard transforms for K-cache - CPU only (#1033)
2025-12-04 06:51:11 +01:00
llama-grammar.cpp
Update grammar (#1023)
2025-11-30 18:45:38 +01:00
llama-grammar.h
Update grammar (#1023)
2025-11-30 18:45:38 +01:00
llama-hparams.cpp
Adding ministral3: this seems to work (#1030)
2025-12-03 11:01:21 +01:00
llama-hparams.h
Adding ministral3: this seems to work (#1030)
2025-12-03 11:01:21 +01:00
llama-impl.h
POC: CUDA tensor parallel (MoE models) (#1022)
2025-12-01 19:25:40 +01:00
llama-load-tensors.cpp
Be able to set a max. number of GPUs to be used in split mode graph (#1051)
2025-12-11 07:22:53 +01:00
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
CUDA: set compute parameters via command line arguments (#910)
2025-11-07 07:11:23 +02:00
llama-model-loader.h
Merge Q, K, V (#878)
2025-10-30 10:49:48 +02:00
llama-model.cpp
Adding ministral3: this seems to work (#1030)
2025-12-03 11:01:21 +01:00
llama-model.h
Be able to set a max. number of GPUs to be used in split mode graph (#1051)
2025-12-11 07:22:53 +01:00
llama-quantize.cpp
Fix requatizing from row-interleaved quants (#992)
2025-11-20 11:50:09 +01:00
llama-sampling.cpp
Update grammar (#1023)
2025-11-30 18:45:38 +01:00
llama-sampling.h
add dry sampler (#513)
2025-06-19 10:24:53 +03:00
llama-vocab.cpp
Update mtmd to improve accuracy of M-RoPE (#993)
2025-11-29 07:27:15 +01:00
llama-vocab.h
Update mtmd to improve accuracy of M-RoPE (#993)
2025-11-29 07:27:15 +01:00
llama.cpp
Slightly faster TG for split mode "graph" (#1057)
2025-12-12 07:54:37 +01:00
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