 Jan Boon
|
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
|
1 year ago |
 Abhilash Majumder
|
87fb5b4234
remove row=1 cond (#6532)
|
1 year ago |
 Firat
|
d752327c33
Adding KodiBot to UI list (#6535)
|
1 year ago |
 Mark Fairbairn
|
855f54402e
Change Windows AMD example to release build to make inference much faster. (#6525)
|
1 year ago |
 Georgi Gerganov
|
b909236c0b
flake.lock: Update (#6517)
|
1 year ago |
 DAN™
|
e0717e751e
Add GritLM as supported models. (#6513)
|
1 year ago |
|
Georgi Gerganov
|
c37247796b
sync : ggml
|
1 year ago |
 Slava Primenko
|
f77261a7c5
ggml: bypass code incompatible with CUDA < 11.1 (whisper/2020)
|
1 year ago |
|
Georgi Gerganov
|
43e8995e75
scripts : sync ggml-cuda folder
|
1 year ago |
 limitedAtonement
|
9472bce308
Run make to build the project (#6457)
|
1 year ago |
 Neo Zhang Jianyu
|
d4f220a5cc
support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M (#6521)
|
1 year ago |
|
Georgi Gerganov
|
54ea0698fb
sync : ggml
|
1 year ago |
 Daniel Bevenius
|
b66aec675c
backend : fix typo in scheduler documentation (ggml/781)
|
1 year ago |
 Clint Herron
|
57dd02c44b
Tests: Added integration tests for GBNF parser (#6472)
|
1 year ago |
 Pierrick Hymbert
|
75cd4c7729
ci: bench: support sse and fix prompt processing time / server: add tokens usage in stream OAI response (#6495)
|
1 year ago |
 Brian
|
a8bd14d557
gguf.py : add licence and version to gguf writer (#6504)
|
1 year ago |
 Hoang Nguyen
|
d0f5deebf8
readme : update UI list (#6503)
|
1 year ago |
 Ting Sun
|
87e21bbacd
bench : make n_batch and n_ubatch configurable in Batched bench (#6500)
|
1 year ago |
 Ouadie EL FAROUKI
|
1b496a745c
[SYCL] Fixed minor bug when enabling FP16 for non intel targets (#6464)
|
1 year ago |
 alexpinel
|
a307375c02
readme : add Dot to UI list (#6487)
|
1 year ago |
 Jun Jie
|
b660a5729e
readme : fix typo (#6481)
|
1 year ago |
 Ed Lepedus
|
0a1d889e27
server: add cURL support to server Dockerfiles (#6474)
|
1 year ago |
 Minsoo Cheong
|
7dda1b727e
ci: exempt master branch workflows from getting cancelled (#6486)
|
1 year ago |
 Ewout ter Hoeven
|
c666ba26c3
build CI: Name artifacts (#6482)
|
1 year ago |
 Shakhar Dasgupta
|
2e66913e5f
server: allow penalizing repetition of newlines on server webpage (#6431)
|
1 year ago |
|
Pierrick Hymbert
|
8120efee1d
ci: bench fix concurrency for workflow trigger dispatch with sha1 (#6478)
|
1 year ago |
|
limitedAtonement
|
a74401f0e5
Correct README link (#6458)
|
1 year ago |
|
Pierrick Hymbert
|
7a2c92637a
ci: bench: add more ftype, fix triggers and bot comment (#6466)
|
1 year ago |
|
Daniel Bevenius
|
4bcd6b959c
common: remove duplicate check for curl (#6471)
|
1 year ago |
|
Clint Herron
|
9b84ae1806
examples : add GBNF validator program (#5948)
|
1 year ago |
