 Nicholai Tukanov
|
368645698a
ggml : add NVPL BLAS support (#8329) (#8425)
|
1 anno fa |
 Daniel Bevenius
|
b078c619aa
cuda : suppress 'noreturn' warn in no_device_code (#8414)
|
1 anno fa |
 Johannes Gäßler
|
808aba3916
CUDA: optimize and refactor MMQ (#8416)
|
1 anno fa |
 Georgi Gerganov
|
a977c11544
gitignore : deprecated binaries
|
1 anno fa |
 compilade
|
9a55ffe6fb
tokenize : add --no-parse-special option (#8423)
|
1 anno fa |
|
Georgi Gerganov
|
7a221b672e
llama : use F32 precision in Qwen2 attention and no FA (#8412)
|
1 anno fa |
 Clint Herron
|
278d0e1846
Initialize default slot sampling parameters from the global context. (#8418)
|
1 anno fa |
|
Clint Herron
|
dd07a123b7
Name Migration: Build the deprecation-warning 'main' binary every time (#8404)
|
1 anno fa |
 AidanBeltonS
|
f4444d992c
[SYCL] Use multi_ptr to clean up deprecated warnings (#8256)
|
1 anno fa |
|
Georgi Gerganov
|
6b2a849d1f
ggml : move sgemm sources to llamafile subfolder (#8394)
|
1 anno fa |
 Dibakar Gope
|
0f1a39f343
ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)
|
1 anno fa |
 M. Yusuf Sarıgöz
|
83321c6958
gguf-py rel pipeline (#8410)
|
1 anno fa |
 Borislav Stanimirov
|
cc61948b1f
llama : C++20 compatibility for u8 strings (#8408)
|
1 anno fa |
|
Borislav Stanimirov
|
7a80710d93
msvc : silence codecvt c++17 deprecation warnings (#8395)
|
1 anno fa |
 fairydreaming
|
a8be1e6f59
llama : add assert about missing llama_encode() call (#8400)
|
1 anno fa |
 RunningLeon
|
e4dd31ff89
py : fix converter for internlm2 (#8321)
|
1 anno fa |
 laik
|
8f0fad42b9
py : fix extra space in convert_hf_to_gguf.py (#8407)
|
1 anno fa |
|
Clint Herron
|
a59f8fdc85
Server: Enable setting default sampling parameters via command-line (#8402)
|
1 anno fa |
 Andy Salerno
|
fd560fe680
Update README.md to fix broken link to docs (#8399)
|
1 anno fa |
|
Clint Herron
|
e500d6135a
Deprecation warning to assist with migration to new binary names (#8283)
|
1 anno fa |
|
Johannes Gäßler
|
a03e8dd99d
make/cmake: LLAMA_NO_CCACHE -> GGML_NO_CCACHE (#8392)
|
1 anno fa |
 Alberto Cabrera Pérez
|
5b0b8d8cfb
sycl : Reenabled mmvq path for the SYCL Nvidia Backend (#8372)
|
1 anno fa |
|
Borislav Stanimirov
|
9925ca4087
cmake : allow external ggml (#8370)
|
1 anno fa |
 daghanerdonmez
|
9beb2dda03
readme : fix typo [no ci] (#8389)
|
1 anno fa |
|
compilade
|
7d0e23d72e
gguf-py : do not use internal numpy types (#7472)
|
1 anno fa |
|
Georgi Gerganov
|
7fdb6f73e3
flake.lock: Update (#8342)
|
1 anno fa |
|
Alberto Cabrera Pérez
|
a130eccef4
labeler : updated sycl to match docs and code refactor (#8373)
|
1 anno fa |
 b4b4o
|
c4dd11d1d3
readme : fix web link error [no ci] (#8347)
|
1 anno fa |
 Alberto Cabrera Pérez
|
2ec846d558
sycl : fix powf call in device code (#8368)
|
1 anno fa |
|
Georgi Gerganov
|
3f2d538b81
scripts : fix sync for sycl
|
1 anno fa |
