 Olivier Chafik
|
396b18dfec
`json`: document schema conversion in GBNF readme, align manual grammar examples & converters (#7841)
|
1 year ago |
 Jared Van Bortel
|
864a99e7a0
cmake : fix CMake requirement for CUDA (#7821)
|
1 year ago |
 slaren
|
fd5ea0f897
ci : try win-2019 on server windows test (#7854)
|
1 year ago |
 Georgi Gerganov
|
c28a83902c
examples : remove --instruct remnants (#7846)
|
1 year ago |
|
Georgi Gerganov
|
d9da0e4986
server : improve "prompt" handling (#7847)
|
1 year ago |
 Johannes Gäßler
|
1f0dabda8d
CUDA: use tensor cores for MMQ (#7676)
|
1 year ago |
 Ben Ashbaugh
|
af4ae502dd
use the correct SYCL context for host USM allocations (#7777)
|
1 year ago |
|
Georgi Gerganov
|
10ceba354a
flake.lock: Update (#7838)
|
1 year ago |
|
Georgi Gerganov
|
e95beeb1fc
imatrix : handle partial entries (#7833)
|
1 year ago |
 Nicolás Pérez
|
57bf62ce7c
docs: Added initial PR template with directions for doc only changes and squash merges [no ci] (#7700)
|
1 year ago |
 mgroeber9110
|
3e2ee44315
server: do not remove whitespace at the start of a completion chunk (#7830)
|
1 year ago |
|
Johannes Gäßler
|
42b53d192f
CUDA: revise q8_1 data layout for mul_mat_q (#7824)
|
1 year ago |
 sasha0552
|
2decf57bc6
convert-hf : set the model name based on cli arg, if present (#7693)
|
1 year ago |
 compilade
|
5795b94182
convert-hf : match model part name prefix and suffix (#7687)
|
1 year ago |
|
compilade
|
ed9f252118
gguf-py : decouple adding metadata from writing in GGUFWriter (#7827)
|
1 year ago |
|
slaren
|
fe1e3917cf
Revert "[SYCL] Update rpc-server.cpp to include SYCL backend (#7682)" (#7808)
|
1 year ago |
|
Olivier Chafik
|
d4d915d351
url: save -mu downloads to new cache location (#7826)
|
1 year ago |
|
sasha0552
|
7a16ce7db2
server : smart slot selection using Longest Common Prefix (#7728)
|
1 year ago |
|
slaren
|
da799b4189
vulkan : reuse parent extra for views (#7806)
|
1 year ago |
 Christian Zhou-Zheng
|
c00fad71e5
gguf-split : change binary multi-byte units to decimal (#7803)
|
1 year ago |
 intelmatt
|
27615f5ab2
cmake : fix BUILD_SHARED_LIBS=ON build (#7784)
|
1 year ago |
|
Johannes Gäßler
|
7027b27d76
server: update cache_prompt documentation [no ci] (#7745)
|
1 year ago |
 woodx
|
a5cabd7649
server : do not get prompt in infill mode (#7286)
|
1 year ago |
 pengxin99
|
d5c938cd77
[SYCL] fix softmax r2r result wrong issue (#7811)
|
1 year ago |
|
slaren
|
c9ee7118d5
check for nans in imatrix and quantize (#7807)
|
1 year ago |
|
Georgi Gerganov
|
ee459f40f6
server : fix --threads-http arg (#7801)
|
1 year ago |
|
Georgi Gerganov
|
f83351f9a6
imatrix : migrate to gpt_params (#7771)
|
1 year ago |
 Clint Herron
|
ad675e1c67
Added support for . (any character) token in grammar engine. (#6467)
|
1 year ago |
 Mattheus Chediak
|
a143c04375
README minor fixes (#7798) [no ci]
|
1 year ago |
|
Olivier Chafik
|
55b2d0849d
grammars: x{min,max} repetition operator (#6640)
|
1 year ago |
