 Sigbjørn Skjæret
|
e562b9714b
common : change --no-penalize-nl to --penalize-nl (#6334)
|
il y a 1 an |
 slaren
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
il y a 1 an |
 Minsoo Cheong
|
64e7b47c69
examples : add "retrieval" (#6193)
|
il y a 1 an |
 Pierrick Hymbert
|
f482bb2e49
common: llama_load_model_from_url split support (#6192)
|
il y a 1 an |
 Johannes Gäßler
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
il y a 1 an |
 Georgi Gerganov
|
56a00f0a2f
common : default --hf-file to --model (#6234)
|
il y a 1 an |
|
Georgi Gerganov
|
80bd33bc2c
common : add HF arg helpers (#6234)
|
il y a 1 an |
|
Georgi Gerganov
|
95d576b48e
metal : pad n_ctx by 32 (#6177)
|
il y a 1 an |
 DAN™
|
fa046eafbc
Fix params underscore convert to dash. (#6203)
|
il y a 1 an |
 Kawrakow
|
76aa30a263
Add ability to use Q5_0, Q5_1, and IQ4_NL for quantized K cache (#6183)
|
il y a 1 an |
|
DAN™
|
4c28b82529
common : print usage on '-h' and '--help' (#6145)
|
il y a 1 an |
|
DAN™
|
496bc79bc2
common : tidy-up argument parsing (#6105)
|
il y a 1 an |
|
Pierrick Hymbert
|
d01b3c4c32
common: llama_load_model_from_url using --model-url (#6098)
|
il y a 1 an |
|
DAN™
|
15961ec04d
common : refactor nested if causing error C1061 on MSVC (#6101)
|
il y a 1 an |
 Theia Vogel
|
877b4d0c62
llama : add support for control vectors (#5970)
|
il y a 1 an |
|
Georgi Gerganov
|
0fd6c1f015
embedding : print cosine similarity (#899)
|
il y a 1 an |
|
slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
il y a 1 an |
|
Georgi Gerganov
|
05b06210c9
llama : more consistent names of count variables (#5994)
|
il y a 1 an |
 SeungWon Jeong
|
fb215c3832
server : normalize embeddings (#5956)
|
il y a 1 an |
 compilade
|
c2101a2e90
llama : support Mamba Selective State Space Models (#5328)
|
il y a 1 an |
|
Georgi Gerganov
|
29ae62d2ae
llama : fix embeddings (#5796)
|
il y a 1 an |
|
Minsoo Cheong
|
6d341ab6c5
speculative : implement stochastic speculative sampling (#5625)
|
il y a 1 an |
 Douglas Hanley
|
475df1d6cf
llama : allow for user specified embedding pooling type (#5849)
|
il y a 1 an |
 Neo Zhang Jianyu
|
715641391d
Support multiple GPUs (split mode) on SYCL backend (#5806)
|
il y a 1 an |
 Miwa / Ensan
|
f49a535686
common : fix flag `--logits-all` to `--all-logits` (#5805)
|
il y a 1 an |
|
Pierrick Hymbert
|
3ab8b3a92e
llama : cleanup unused mmq flags (#5772)
|
il y a 1 an |
|
Georgi Gerganov
|
9d533a77d0
llama : fix defrag bugs + add parameter (#5735)
|
il y a 1 an |
|
Georgi Gerganov
|
ab336a9d5e
code : normalize enum names (#5697)
|
il y a 1 an |
 Robey Holderith
|
5ee99c32f5
common, server : surface min_keep as its own parameter (#5567)
|
il y a 1 an |
|
Georgi Gerganov
|
1dcc3fde00
common : fix ub (#5530)
|
il y a 1 an |
