 Jared Van Bortel
|
864a99e7a0
cmake : fix CMake requirement for CUDA (#7821)
|
1 year ago |
 Johannes Gäßler
|
7d1a378b8f
CUDA: refactor mmq, dmmv, mmvq (#7716)
|
1 year ago |
 Georgi Gerganov
|
554c247caf
ggml : remove OpenCL (#7735)
|
1 year ago |
 Daniele
|
987d743d6b
Improve hipBLAS support in CMake (#7696)
|
1 year ago |
 Masaya, Kato
|
a5735e4426
ggml : use OpenMP as a thread pool (#7606)
|
1 year ago |
 Andy Tai
|
a10cda58d3
cmake : add pkg-config spec file for llama.cpp (#7702)
|
1 year ago |
 woachk
|
9e405b6e2e
kompute : implement op_getrows_f32 (#6403)
|
1 year ago |
|
Johannes Gäßler
|
9b596417af
CUDA: quantized KV support for FA vec (#7527)
|
1 year ago |
 Galunid
|
9c4c9cc83f
Move convert.py to examples/convert-legacy-llama.py (#7430)
|
1 year ago |
 Meng, Hengyu
|
b864b50ce5
[SYCL] Align GEMM dispatch (#7566)
|
1 year ago |
|
Masaya, Kato
|
faa0e6979a
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
|
1 year ago |
|
Georgi Gerganov
|
e84b71c2c6
ggml : drop support for QK_K=64 (#7473)
|
1 year ago |
 k.h.lai
|
fcda1128bc
vulkan: add workaround for iterator boundary check to fix clang-cl debug build (#7426)
|
1 year ago |
 junchao-loongson
|
65c58207ec
ggml : add loongarch lsx and lasx support (#6454)
|
1 year ago |
 Srihari-mcw
|
33c8d50acc
Add provisions for windows support for BF16 code including CMake provision for enabling AVX512_BF16 (#7258)
|
1 year ago |
 slaren
|
d359f30921
llama : remove MPI backend (#7395)
|
1 year ago |
|
Georgi Gerganov
|
059031b8c4
ci : re-enable sanitizer runs (#7358)
|
1 year ago |
 Engininja2
|
ef277de2ad
cmake : fix typo in AMDGPU_TARGETS (#7356)
|
1 year ago |
 Gavin Zhao
|
82ca83db3c
ROCm: use native CMake HIP support (#5966)
|
1 year ago |
 Max Krasnyansky
|
13ad16af12
Add support for properly optimized Windows ARM64 builds with LLVM and MSVC (#7191)
|
1 year ago |
 Radoslav Gerganov
|
5e31828d3e
ggml : add RPC backend (#6829)
|
1 year ago |
|
Georgi Gerganov
|
6f1b63606f
cmake : fix version cmp (#7227)
|
1 year ago |
|
slaren
|
b228aba91a
remove convert-lora-to-ggml.py (#7204)
|
1 year ago |
|
Jared Van Bortel
|
4426e2987b
cmake : fix typo (#7151)
|
1 year ago |
 agray3
|
bc4bba364f
Introduction of CUDA Graphs to LLama.cpp (#6766)
|
1 year ago |
 William Tambellini
|
858f6b73f6
Add an option to build without CUDA VMM (#7067)
|
1 year ago |
|
Georgi Gerganov
|
dba497e0c1
cmake : restore LLAMA_LLAMAFILE_DEFAULT
|
1 year ago |
|
Georgi Gerganov
|
fa0b4ad252
cmake : remove obsolete ANDROID check
|
1 year ago |
 Justine Tunney
|
192090bae4
llamafile : improve sgemm.cpp (#6796)
|
1 year ago |
|
Georgi Gerganov
|
3b8f1ec4b1
llamafile : tmp disable + build sgemm.o when needed (#6716)
|
1 year ago |
