nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ik_llama_opt/ggml/src
History
Kawrakow ac4ec50f03 CUDA: muh faster prompt processing for MoE models and small u-batch sizes (#728) 
* WIP: adding mainline mmq_id implementation

* This seems to work

* Now also -fmoe works

* WIP

* WIP

* WIP

* This works for mainline supported quants

* mmq_id: add iq2_k, iq2_k_r4

* mmiq_id: don't assume row size is multiple of type size (per row scales)

* mmiq_id: don't assume row size is multiple of type size

* mmq_id: add iq2_ks

So we are sure it works with per row scales

* mmq_id: add iq2_kl

* mmq_id: add iq3_ks

* mmq_id: adding iq3_k, iq3_k_r4

* mmq_id: add iq4_kss, iq4_ks, iq4_ks_r4

* mmq_id: adding iq4_k, iq4_k_r4

* mmq_id: adding iq5_ks, iq5_ks_r4

* mmq_id: adding iq5_k, iq5_k_r4, q6_0

* mmq_id: adding iq6_k

* mmq_id: add iq1_s_r4

* mmq_id: adding iq1_kt, iq2_kt

* mmq_id: add iq3_kt, iq4_kt

* Add CUDA fp8 header

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 		2025-08-26 13:30:35 +03:00
..
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 CUDA: muh faster prompt processing for MoE models and small u-batch sizes (#728) 2025-08-26 13:30:35 +03:00
ggml-sycl Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
iqk Log for debugging #721 (#722) 2025-08-23 15:24:34 +03:00
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 Vulkan: a fresh start (#608) 2025-07-15 08:03:13 +02:00
CMakeLists.txt Vulkan: add cmake options to build without coopmat(2) support (#674) 2025-08-07 17:26:21 +03:00
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.c Fix debug build failure with RPC off (#579) 2025-07-03 15:26:28 +02:00
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 CUDA: muh faster prompt processing for MoE models and small u-batch sizes (#728) 2025-08-26 13:30:35 +03:00
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 AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710) 2025-08-22 06:27:07 +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 Merge vulkan code from mainline up to commit of 6/28/2025 (#563) 2025-07-02 08:49:42 +02:00
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 Vulkan: a fresh start (#608) 2025-07-15 08:03:13 +02:00
ggml.c AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710) 2025-08-22 06:27:07 +03:00