tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-05 08:28:37 -04:00
Code Issues Packages Projects Releases Wiki Activity
Files
96b3d411e0469c478100ec72ae5fb758544dc3ba
llama.cpp/ggml/src
History
Francis Couture-Harpin 96b3d411e0 ggml-quants : allow using vdotq_s32 in TQ2_0 vec_dot 
Not yet tested on harware which supports it,
might not work or might not even compile. But also it might.
It should make the performance better on recent ARM CPUs.

* ggml-quants : remove comment about possible format change of TQ2_0

Making it slightly more convenient for AVX512
but less convenient for everything else is not worth the trouble.
2024-08-07 15:08:41 -04:00
..
ggml-cann
ggml : reduce hash table reset cost (#8698)
2024-07-27 04:41:55 +02:00
ggml-cuda
feat: Support Moore Threads GPU (#8383)
2024-07-28 01:41:25 +02:00
ggml-sycl
ggml : reduce hash table reset cost (#8698)
2024-07-27 04:41:55 +02:00
kompute @ 4565194ed7
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
kompute-shaders
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
llamafile
ggml : move sgemm sources to llamafile subfolder (#8394)
2024-07-10 15:23:29 +03:00
vulkan-shaders
chore : Fix vulkan related compiler warnings, add help text, improve CLI options (#8477)
2024-07-28 09:52:42 +02:00
CMakeLists.txt
feat: Support Moore Threads GPU (#8383)
2024-07-28 01:41:25 +02:00
ggml-aarch64.c
ggml : fix build on Windows with Snapdragon X (#8531)
2024-07-25 19:01:00 +03:00
ggml-aarch64.h
ggml : minor naming changes (#8433)
2024-07-12 10:46:02 +03:00
ggml-alloc.c
ggml : reduce hash table reset cost (#8698)
2024-07-27 04:41:55 +02:00
ggml-backend-impl.h
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
ggml-backend.c
ggml : reduce hash table reset cost (#8698)
2024-07-27 04:41:55 +02:00
ggml-blas.cpp
ggml : reduce hash table reset cost (#8698)
2024-07-27 04:41:55 +02:00
ggml-cann.cpp
cann: Fix Multi-NPU execution error (#8710)
2024-07-27 16:36:44 +08:00
ggml-common.h
ggml-quants : rename fields of TQ1_0 and TQ2_0 structs for consistency
2024-08-03 16:22:04 -04:00
ggml-cuda.cu
feat: Support Moore Threads GPU (#8383)
2024-07-28 01:41:25 +02:00
ggml-impl.h
Merge branch 'master' into compilade/bitnet-ternary
2024-07-28 21:27:33 -04:00
ggml-kompute.cpp
ggml : reduce hash table reset cost (#8698)
2024-07-27 04:41:55 +02:00
ggml-metal.m
ggml : reduce hash table reset cost (#8698)
2024-07-27 04:41:55 +02:00
ggml-metal.metal
ggml : fix quant dot product with odd number of blocks (#8549)
2024-07-19 17:17:27 +02:00
ggml-quants.c
ggml-quants : allow using vdotq_s32 in TQ2_0 vec_dot
2024-08-07 15:08:41 -04:00
ggml-quants.h
ggml : remove q1_3 and q2_2
2024-08-02 20:16:26 -04:00
ggml-rpc.cpp
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
ggml-sycl.cpp
ggml : reduce hash table reset cost (#8698)
2024-07-27 04:41:55 +02:00
ggml-vulkan.cpp
vulkan : initialize vk_buffer_struct members to VK_NULL_HANDLE (ggml/893)
2024-07-27 17:43:44 +03:00
ggml.c
ggml : remove q1_3 and q2_2
2024-08-02 20:16:26 -04:00