 Georgi Gerganov
|
f3f28c5395
cmake : fix GGML_USE_SYCL typo (#5555)
|
hai 1 ano |
 Pierrick Hymbert
|
e75c6279d1
server : enhanced health endpoint (#5548)
|
hai 1 ano |
|
Pierrick Hymbert
|
36376abe05
server : --n-predict option document and cap to max value (#5549)
|
hai 1 ano |
 Daniel Hiltgen
|
66c1968f7a
server : graceful server shutdown (#5244)
|
hai 1 ano |
|
Georgi Gerganov
|
1dcc3fde00
common : fix ub (#5530)
|
hai 1 ano |
 Herman Semenov
|
5d3de51f97
ggml, common, examples, tests : fixed type arguments in printf (#5528)
|
hai 1 ano |
 Daniel Bevenius
|
fc0c8d286a
llava : update surgery script to not remove tensors (#5536)
|
hai 1 ano |
 Kawrakow
|
bd2d4e393b
1.5 bit quantization (#5453)
|
hai 1 ano |
 github-actions[bot]
|
c8e0d7efeb
flake.lock: Update
|
hai 1 ano |
|
Georgi Gerganov
|
8f1be0d42f
ggml : add ALiBi support for ggml_soft_max_ext (#5488)
|
hai 1 ano |
 Ananta Bastola
|
6e4e973b26
ci : add an option to fail on compile warning (#3952)
|
hai 1 ano |
 clibdev
|
d250c9d61d
gitignore : update for CLion IDE (#5544)
|
hai 1 ano |
|
Georgi Gerganov
|
5bf2b94dd4
cmake : fix VULKAN and ROCm builds (#5525)
|
hai 1 ano |
|
Georgi Gerganov
|
d2819d5577
scripts : add helpers script for bench comparing commits (#5521)
|
hai 1 ano |
|
Herman Semenov
|
4cb0727698
llava : removed excess free(NULL) operation (#5531)
|
hai 1 ano |
|
Herman Semenov
|
65085c713e
llama : minor fixed return int value (#5529)
|
hai 1 ano |
 Alexey Parfenov
|
6dcc02d244
server : add "samplers" param to control the samplers order (#5494)
|
hai 1 ano |
 Rőczey Barnabás
|
5f5808ca7b
server : fix system prompt cli (#5516)
|
hai 1 ano |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
hai 1 ano |
|
Daniel Bevenius
|
60ed04cf82
llava : fix clip-model-is-vision flag in README.md (#5509)
|
hai 1 ano |
|
Georgi Gerganov
|
594845aab1
ci : fix BERT model download and convert
|
hai 1 ano |
 Douglas Hanley
|
4524290e87
Use correct type of pooling for embedding models (#5500)
|
hai 1 ano |
|
Georgi Gerganov
|
c06e45d729
clip : fix wrong loop condition
|
hai 1 ano |
 slaren
|
9060a1e9df
cuda : print message when initialization fails (#5512)
|
hai 1 ano |
|
Georgi Gerganov
|
9350a1cf21
scripts : add hf.sh helper script (#5501)
|
hai 1 ano |
 Michaël de Vries
|
73122473ff
fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false (#5487)
|
hai 1 ano |
 Elbios
|
0d4177126b
llava : fix memory management bug (#5491)
|
hai 1 ano |
 John
|
7930a8a6e8
llaba : hotfix for llava-1.6 image number (#5495)
|
hai 1 ano |
 Neuman Vong
|
704359e299
vulkan: Find optimal memory type but with fallback (#5381)
|
hai 1 ano |
 Rune
|
594fca3fef
readme : fix typo (#5490)
|
hai 1 ano |
