ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-11 00:40:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
f90d1fdd06d25bd4ebc2cf4830c98b279074a892
ik_llama.cpp/ggml/src
History
Kawrakow f90d1fdd06 Split mode "graph" for Cohere2 (#1061) 
* This works and TG is descent, but PP is low

* Better

* Apply f_logit_scale before mul mat with output tensor

* This is better for PP: 600 t/s -> 700 t/s

* To not lose this again

* WIP

* Equal split

* WIP

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-12-13 20:30:08 +01:00
..
cmake
Merge vulkan code from mainline up to commit of 6/28/2025 (#563)
2025-07-02 08:49:42 +02:00
ggml-cann
Merge mainline - Aug 12 2024 (#17)
2024-08-12 15:14:32 +02:00
ggml-cuda
Split mode "graph" for Cohere2 (#1061)
2025-12-13 20:30:08 +01:00
ggml-sycl
Merge mainline - Aug 12 2024 (#17)
2024-08-12 15:14:32 +02:00
iqk
Unroll for loop for repacked BF16 MATMUL (#1047)
2025-12-08 06:09:45 +01:00
kompute @ 4565194ed7
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
kompute-shaders
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
llamafile
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
vulkan-shaders
Port of Qwen3-VL support from mainline (#883)
2025-11-04 19:20:54 +02:00
CMakeLists.txt
Support GigaChat3 (#995)
2025-11-24 06:55:14 +01:00
ggml-aarch64.c
Merge mainline - Aug 12 2024 (#17)
2024-08-12 15:14:32 +02:00
ggml-aarch64.h
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
ggml-alloc.c
Enable CUDA graphs for MoE models + GPT-OSS support (#689)
2025-08-15 09:18:07 +03:00
ggml-backend-impl.h
Merge vulkan code from mainline up to commit of 6/28/2025 (#563)
2025-07-02 08:49:42 +02:00
ggml-backend.cpp
Split mode "graph" for Cohere2 (#1061)
2025-12-13 20:30:08 +01:00
ggml-blas.cpp
Merge mainline - Aug 12 2024 (#17)
2024-08-12 15:14:32 +02:00
ggml-cann.cpp
Merge vulkan code from mainline up to commit of 6/28/2025 (#563)
2025-07-02 08:49:42 +02:00
ggml-common.h
AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710)
2025-08-22 06:27:07 +03:00
ggml-cuda.cu
Split mode "graph" for Cohere2 (#1061)
2025-12-13 20:30:08 +01:00
ggml-impl.h
MXFP4 (#682)
2025-08-09 08:40:18 +03:00
ggml-kompute.cpp
Merge vulkan code from mainline up to commit of 6/28/2025 (#563)
2025-07-02 08:49:42 +02:00
ggml-metal.m
MXFP4 (#682)
2025-08-09 08:40:18 +03:00
ggml-metal.metal
MXFP4 (#682)
2025-08-09 08:40:18 +03:00
ggml-quants.c
Fix avx2 GEMM mess (v2) (#724)
2025-08-27 08:03:47 +03:00
ggml-quants.h
IQ1_M_R4: better 1.75 bpw quants (#187)
2025-02-06 14:08:52 +02:00
ggml-rpc.cpp
RPC: support multiple devices including cpu (#1024)
2025-11-30 18:48:02 +01:00
ggml-sycl.cpp
Merge vulkan code from mainline up to commit of 6/28/2025 (#563)
2025-07-02 08:49:42 +02:00
ggml-vulkan.cpp
Port of Qwen3-VL support from mainline (#883)
2025-11-04 19:20:54 +02:00
ggml.c
Split mode "graph" for Cohere2 (#1061)
2025-12-13 20:30:08 +01:00