 slaren
|
8172ee9da9
cmake : fix deprecated option names not working (#8171)
|
1 rok pred |
|
slaren
|
31ec3993f6
ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (#8140)
|
1 rok pred |
 Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 rok pred |
 Johannes Gäßler
|
a818f3028d
CUDA: use MMQ instead of cuBLAS by default (#8075)
|
1 rok pred |
|
slaren
|
95f57bb5d5
ggml : remove ggml_task_type and GGML_PERF (#8017)
|
1 rok pred |
 luoyu-intel
|
de391e4c80
[SYCL] Fix windows build and inference (#8003)
|
1 rok pred |
 0cc4m
|
7c7836d9d4
Vulkan Shader Refactor, Memory Debugging Option (#7947)
|
1 rok pred |
 Meng, Hengyu
|
7b2f4a7d19
[SYCL] remove global variables (#7710)
|
1 rok pred |
|
slaren
|
f578b86b21
move BLAS to a separate backend (#6210)
|
1 rok pred |
 Jared Van Bortel
|
864a99e7a0
cmake : fix CMake requirement for CUDA (#7821)
|
1 rok pred |
|
Johannes Gäßler
|
7d1a378b8f
CUDA: refactor mmq, dmmv, mmvq (#7716)
|
1 rok pred |
|
Georgi Gerganov
|
554c247caf
ggml : remove OpenCL (#7735)
|
1 rok pred |
 Daniele
|
987d743d6b
Improve hipBLAS support in CMake (#7696)
|
1 rok pred |
 Masaya, Kato
|
a5735e4426
ggml : use OpenMP as a thread pool (#7606)
|
1 rok pred |
 Andy Tai
|
a10cda58d3
cmake : add pkg-config spec file for llama.cpp (#7702)
|
1 rok pred |
 woachk
|
9e405b6e2e
kompute : implement op_getrows_f32 (#6403)
|
1 rok pred |
|
Johannes Gäßler
|
9b596417af
CUDA: quantized KV support for FA vec (#7527)
|
1 rok pred |
 Galunid
|
9c4c9cc83f
Move convert.py to examples/convert-legacy-llama.py (#7430)
|
1 rok pred |
|
Meng, Hengyu
|
b864b50ce5
[SYCL] Align GEMM dispatch (#7566)
|
1 rok pred |
|
Masaya, Kato
|
faa0e6979a
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
|
1 rok pred |
|
Georgi Gerganov
|
e84b71c2c6
ggml : drop support for QK_K=64 (#7473)
|
1 rok pred |
 k.h.lai
|
fcda1128bc
vulkan: add workaround for iterator boundary check to fix clang-cl debug build (#7426)
|
1 rok pred |
 junchao-loongson
|
65c58207ec
ggml : add loongarch lsx and lasx support (#6454)
|
1 rok pred |
 Srihari-mcw
|
33c8d50acc
Add provisions for windows support for BF16 code including CMake provision for enabling AVX512_BF16 (#7258)
|
1 rok pred |
|
slaren
|
d359f30921
llama : remove MPI backend (#7395)
|
1 rok pred |
|
Georgi Gerganov
|
059031b8c4
ci : re-enable sanitizer runs (#7358)
|
1 rok pred |
 Engininja2
|
ef277de2ad
cmake : fix typo in AMDGPU_TARGETS (#7356)
|
1 rok pred |
 Gavin Zhao
|
82ca83db3c
ROCm: use native CMake HIP support (#5966)
|
1 rok pred |
 Max Krasnyansky
|
13ad16af12
Add support for properly optimized Windows ARM64 builds with LLVM and MSVC (#7191)
|
1 rok pred |
 Radoslav Gerganov
|
5e31828d3e
ggml : add RPC backend (#6829)
|
1 rok pred |
