 Olivier Chafik
|
d4d915d351
url: save -mu downloads to new cache location (#7826)
|
преди 1 година |
 sasha0552
|
7a16ce7db2
server : smart slot selection using Longest Common Prefix (#7728)
|
преди 1 година |
 Georgi Gerganov
|
ee459f40f6
server : fix --threads-http arg (#7801)
|
преди 1 година |
|
Georgi Gerganov
|
f83351f9a6
imatrix : migrate to gpt_params (#7771)
|
преди 1 година |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
преди 1 година |
 Brian
|
d298382ad9
main: replace --no-special with --special (#7534)
|
преди 1 година |
 Justine Tunney
|
00c6390793
main : don't print special tokens with --grammar (#6923)
|
преди 1 година |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
преди 1 година |
 Amir
|
11474e756d
examples: cache hf model when --model not provided (#7353)
|
преди 1 година |
 Radoslav Gerganov
|
5e31828d3e
ggml : add RPC backend (#6829)
|
преди 1 година |
 HanishKVC
|
f89fe2732c
Main+: optionally allow special tokens from user in interactive mode (#7097)
|
преди 1 година |
 Dawid Potocki
|
83330d8cd6
main : add --conversation / -cnv flag (#7108)
|
преди 1 година |
 Johannes Gäßler
|
a8f9b07631
perplexity: more statistics, added documentation (#6936)
|
преди 1 година |
|
Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
преди 1 година |
|
Olivier Chafik
|
8843a98c2b
Improve usability of --model-url & related flags (#6930)
|
преди 1 година |
 cpumaxx
|
ffe666572f
llava-cli : multiple images (#6969)
|
преди 1 година |
|
Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
преди 1 година |
 Pierrick Hymbert
|
0c4d489e29
quantize: add imatrix and dataset metadata in GGUF (#6658)
|
преди 1 година |
 slaren
|
017e6999b5
add basic tensor data validation function (#6884)
|
преди 1 година |
 Douglas Hanley
|
b4e4b8a935
llama : add llama_get_pooling_type function (#6862)
|
преди 1 година |
 Kyle Mistele
|
37246b1031
common : revert showing control tokens by default for server (#6860)
|
преди 1 година |
|
Justine Tunney
|
8cc91dc63c
ggml : add llamafile sgemm (#6414)
|
преди 1 година |
|
Pierrick Hymbert
|
b804b1ef77
eval-callback: Example how to use eval callback for debugging (#6576)
|
преди 1 година |
 Jared Van Bortel
|
1b67731e18
BERT tokenizer fixes (#6498)
|
преди 1 година |
 Jan Boon
|
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
|
преди 1 година |
 Minsoo Cheong
|
64e7b47c69
examples : add "retrieval" (#6193)
|
преди 1 година |
|
Pierrick Hymbert
|
f482bb2e49
common: llama_load_model_from_url split support (#6192)
|
преди 1 година |
|
Johannes Gäßler
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
преди 1 година |
|
Georgi Gerganov
|
80bd33bc2c
common : add HF arg helpers (#6234)
|
преди 1 година |
|
Georgi Gerganov
|
68e210b354
server : enable continuous batching by default (#6231)
|
преди 1 година |
