 Akarshan Biswas
|
991f8aabee
SYCL: Fix and switch to GGML_LOG system instead of fprintf (#10579)
|
1 year ago |
 Georgi Gerganov
|
4cb003dd8d
contrib : refresh (#10593)
|
1 year ago |
 Juk Armstrong
|
917786f43d
Add `mistral-v1`, `mistral-v3`, `mistral-v3-tekken` and `mistral-v7` chat template types (#10572)
|
1 year ago |
|
Georgi Gerganov
|
5e1ed95583
grammars : add English-only grammar (#10612)
|
1 year ago |
 Wang Qin
|
5c7a5aa0c3
ci: add error handling for Python venv creation in run.sh (#10608)
|
1 year ago |
 Diego Devesa
|
3420909dff
ggml : automatic selection of best CPU backend (#10606)
|
1 year ago |
 alek3y
|
86dc11c5bc
server : bind to any port when specified (#10590)
|
1 year ago |
|
Georgi Gerganov
|
6acce39710
readme : update the usage section with examples (#10596)
|
1 year ago |
|
Wang Qin
|
43957ef203
build: update Makefile comments for C++ version change (#10598)
|
1 year ago |
 Adrien Gallouët
|
0c39f44d70
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0() (#10567)
|
1 year ago |
|
Georgi Gerganov
|
3e0ba0e604
readme : remove old badge
|
1 year ago |
|
Georgi Gerganov
|
abadba05be
readme : refresh (#10587)
|
1 year ago |
 Eve
|
0533e7fb38
vulkan: Dynamic subgroup size support for Q6_K mat_vec (#10536)
|
1 year ago |
|
Diego Devesa
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
1 year ago |
 Xuan Son Nguyen
|
b782e5c7d4
server : add more test cases (#10569)
|
1 year ago |
 Robert Collins
|
3a8e9af402
imatrix : support combine-only (#10492)
|
1 year ago |
|
Diego Devesa
|
a3a3048e7a
cleanup UI link list (#10577)
|
1 year ago |
|
Georgi Gerganov
|
f0678c5ff4
ggml : fix I8MM Q4_1 scaling factor conversion (#10562)
|
1 year ago |
 Shupei Fan
|
4b3242bbea
ggml-cpu: fix typo in gemv/gemm iq4_nl_4_4 (#10580)
|
1 year ago |
 Alberto Cabrera Pérez
|
0f77aae560
sycl : offload of get_rows set to 0 (#10432)
|
1 year ago |
|
Alberto Cabrera Pérez
|
266b8519ee
sycl : Reroute permuted mul_mats through oneMKL (#10408)
|
1 year ago |
 Chenguang Li
|
938f608742
CANN: RoPE operator optimization (#10563)
|
1 year ago |
 Jeff Bolz
|
f095a649ec
vulkan: get the first command buffer submitted sooner (#10499)
|
1 year ago |
 Ting Lou
|
678d7994f4
llava: return false instead of exit (#10546)
|
1 year ago |
|
Georgi Gerganov
|
dc22344088
ggml : remove redundant copyright notice + update authors
|
1 year ago |
|
Georgi Gerganov
|
4c0a95b107
llama : add missing model types
|
1 year ago |
|
Xuan Son Nguyen
|
6c59567689
server : (tests) don't use thread for capturing stdout/stderr, bump openai client library (#10568)
|
1 year ago |
 Johannes Gäßler
|
890719311b
common: fix warning message when no GPU found (#10564)
|
1 year ago |
 Random Fly
|
7281cf13ad
docs: fix outdated usage of llama-simple (#10565)
|
1 year ago |
|
Diego Devesa
|
e90688edd0
ci : fix tag name in cuda and hip releases (#10566)
|
1 year ago |
