 Georgi Gerganov
|
190c4838bd
chat : reserve memory in compute_diffs and improve naming (#17729)
|
1 месяц назад |
 Pascal
|
e7c2cf1356
server: add router multi-model tests (#17704) (#17722)
|
1 месяц назад |
 Adrien Gallouët
|
1257491047
server : fix bad fmt, size() is a size_type (#17735)
|
1 месяц назад |
|
Adrien Gallouët
|
083e18b11c
cmake: explicitly link against crypt32 on non-MSVC Windows builds (#17727)
|
1 месяц назад |
|
Georgi Gerganov
|
3d94e967a1
metal : fix data race in pipeline library (#17731)
|
1 месяц назад |
 jiahao su
|
7feb0a1005
ci : remove the build of openeuler-cann in release (#17724)
|
1 месяц назад |
 Aldehir Rojas
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
1 месяц назад |
|
Pascal
|
5ceed62421
server: fix duplicate HTTP headers in multiple models mode (#17698)
|
1 месяц назад |
 Reese Levine
|
7ca5991d2b
ggml webgpu: add support for emscripten builds (#17184)
|
1 месяц назад |
 Sigbjørn Skjæret
|
b3e3060f4e
ci : move release details to the top visible by default (#17719)
|
1 месяц назад |
 Herman Semenoff
|
37adc9c6ba
ggml, llama : use defaulted constructors/destructors (#17649)
|
1 месяц назад |
 Marcos Del Sol Vives
|
16cc3c606e
build: document how to compile with Vulkan using Debian/Ubuntu packages (#17688)
|
1 месяц назад |
 Xuan-Son Nguyen
|
13628d8bdb
server: add --media-path for local media files (#17697)
|
1 месяц назад |
|
Xuan-Son Nguyen
|
a96283adc4
mtmd: fix --no-warmup (#17695)
|
1 месяц назад |
 Ali Tariq
|
4eba8d9451
ci : RVV1.0 builds with tests (#16682)
|
1 месяц назад |
 Jeff Bolz
|
61bde8e21f
vulkan: Reduce temporary memory usage for TOP_K (#17623)
|
1 месяц назад |
 xiaobing318
|
e251e5ebbe
cmake : add utf8 compilation options for msvc (#17682)
|
1 месяц назад |
 Chad Voegele
|
c4357dcc35
Server: Change Invalid Schema from Server Error (500) to User Error (400) (#17572)
|
1 месяц назад |
|
Adrien Gallouët
|
e148380c7c
ggml : use svcntb() for SVE vector length detection (#17474)
|
1 месяц назад |
 TianHao324
|
a2b0fe8d37
CANN: Disable Ger operator of OUT_PROD on 310p device (#17563)
|
1 месяц назад |
 Daniel Bevenius
|
7f3a72a8ed
ggml : remove redundant n_copies check when setting input/output (#17612)
|
1 месяц назад |
 Eric Curtin
|
b9a37717b0
codeowners : remove ericcurtin (#17658)
|
1 месяц назад |
|
Adrien Gallouët
|
f3a9674ae8
llama : fix signed comparison warning on FreeBSD (#17497)
|
1 месяц назад |
|
Xuan-Son Nguyen
|
2c453c6c77
convert: add error message for mistral3 quantized weight (#17686)
|
1 месяц назад |
|
Xuan-Son Nguyen
|
5d6bd842ea
server: remove default "gpt-3.5-turbo" model name (#17668)
|
1 месяц назад |
 senhtry
|
fd3abe849e
server: fixing naming conflict res_error in server-models.cpp (#17679)
|
1 месяц назад |
|
Xuan-Son Nguyen
|
682e6658bb
server: explicitly set exec path when create new instance (#17669)
|
1 месяц назад |
|
Adrien Gallouët
|
4574f2949e
ci : skip winget update when not in ggml-org (#17465)
|
1 месяц назад |
|
Adrien Gallouët
|
ab6726eeff
ggml : add fallback definition for HWCAP2_SVE2 (#17683)
|
1 месяц назад |
 Aleksander Grygier
|
cee92af553
Add context info to server error (#17663)
|
1 месяц назад |
