Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-27 12:33:06 +01:00
Code Issues Packages Projects Releases Wiki Activity
b4320
llama.cpp/ggml/src
History
Eve 64ae065511
vulkan: small mul_mat_vec optimizations (#10665) 
* double the number of rows per workgroup

* Update ggml-vulkan.cpp

* Vulkan: Add VK_EXT_subgroup_size_control support to ensure full subgroups for coopmats

* only increase the number of rows for amd and subgroup size 64

* fix missing NUM_ROWS for mul_mat_vec_iq4_nl_f16_f32, untested

* use subgroup min and max to check for gcn (requires https://github.com/ggerganov/llama.cpp/pull/10721)

* manual merge ggml-vulkan.cpp

* set min and max subgroup size in any case

* Also double the number of rows for Intel GPUs
2024-12-13 09:42:04 +01:00
..
ggml-blas ggml : add support for dynamic loading of backends (#10469) 2024-11-25 15:13:39 +01:00
ggml-cann ggml : refactor online repacking (#10446) 2024-12-07 14:37:50 +02:00
ggml-cpu ggml : Fix compilation issues on ARM platform when building without fp16 (#10811) 2024-12-13 01:04:19 +01:00
ggml-cuda CUDA: faster non-contiguous concat (#10760) 2024-12-12 19:09:50 +01:00
ggml-hip ggml : add support for dynamic loading of backends (#10469) 2024-11-25 15:13:39 +01:00
ggml-kompute kompute : improve backend to pass test_backend_ops (#10542) 2024-11-28 12:51:38 +01:00
ggml-metal metal : Extend how Llama.cpp locates metal resources (#10676) 2024-12-07 09:55:01 +02:00
ggml-musa mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516) 2024-11-26 17:00:41 +01:00
ggml-rpc ggml : add support for dynamic loading of backends (#10469) 2024-11-25 15:13:39 +01:00
ggml-sycl SYCL: Reduce most of the compiler warnings (#10748) 2024-12-13 12:12:15 +05:30
ggml-vulkan vulkan: small mul_mat_vec optimizations (#10665) 2024-12-13 09:42:04 +01:00
CMakeLists.txt remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 2024-12-12 19:02:49 +01:00
ggml-alloc.c ggml: new optimization interface (ggml/988) 2024-11-17 08:30:29 +02:00
ggml-backend-impl.h ggml : automatic selection of best CPU backend (#10606) 2024-12-01 16:12:41 +01:00
ggml-backend-reg.cpp ggml: load all backends from a user-provided search path (#10699) 2024-12-11 01:47:21 +01:00
ggml-backend.cpp ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
ggml-common.h CUDA: rename macros to avoid conflicts with WinAPI (#10736) 2024-12-10 18:23:24 +01:00
ggml-impl.h remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 2024-12-12 19:02:49 +01:00
ggml-opt.cpp ggml-opt: fix data corruption (ggml/1022) 2024-11-21 09:22:02 +02:00
ggml-quants.c ggml : refactor online repacking (#10446) 2024-12-07 14:37:50 +02:00
ggml-quants.h ggml : build backends as libraries (#10256) 2024-11-14 18:04:35 +01:00
ggml-threading.cpp ggml : build backends as libraries (#10256) 2024-11-14 18:04:35 +01:00
ggml-threading.h remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 2024-12-12 19:02:49 +01:00
ggml.c ggml : refactor online repacking (#10446) 2024-12-07 14:37:50 +02:00