 Georgi Gerganov
|
4301e27319
common : restore grammar-based rejection sampling (#18137)
|
1 mese fa |
|
Georgi Gerganov
|
254098a279
common : refactor common_sampler + grammar logic changes (#17937)
|
1 mese fa |
|
Georgi Gerganov
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
4 mesi fa |
 Michał Moskal
|
ff227703d6
sampling : support for llguidance grammars (#10224)
|
11 mesi fa |
|
Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
1 anno fa |
 Diego Devesa
|
7eee341bee
common : use common_ prefix for common library functions (#9805)
|
1 anno fa |
|
slaren
|
49006c67b4
llama : move random seed generation to the samplers (#9398)
|
1 anno fa |
 Xuan Son Nguyen
|
bfe76d4a17
common : move arg parser code to `arg.cpp` (#9388)
|
1 anno fa |
|
Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
1 anno fa |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
1 anno fa |
 Johannes Gäßler
|
5ae3426b0b
server: fix reported top tokens for temperature 0 (#7203)
|
1 anno fa |
|
Johannes Gäßler
|
af0a5b6163
server: fix incorrectly reported token probabilities (#7125)
|
1 anno fa |
|
Johannes Gäßler
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
1 anno fa |
 Rick G
|
e3c337d87c
llama : support negative ith in llama_get_ API (#6519)
|
1 anno fa |
 Minsoo Cheong
|
586e7bc561
sampling : deduplicated code for probability distribution access (#6240)
|
1 anno fa |
|
Georgi Gerganov
|
b80cf3b2d1
common : disable repeat penalties by default (#6127)
|
1 anno fa |
|
Minsoo Cheong
|
6d341ab6c5
speculative : implement stochastic speculative sampling (#5625)
|
1 anno fa |
 Robey Holderith
|
5ee99c32f5
common, server : surface min_keep as its own parameter (#5567)
|
1 anno fa |
 Alexey Parfenov
|
6dcc02d244
server : add "samplers" param to control the samplers order (#5494)
|
1 anno fa |
|
Alexey Parfenov
|
a803333a4e
common : use enums for sampler types (#5418)
|
1 anno fa |
 l3utterfly
|
5eaf9964fc
llama : dynamic temperature sampling (#4972)
|
2 anni fa |
 David Renshaw
|
f46c0c1b0e
llama : fix copy/paste error in llama_sampling_params comment (#4994)
|
2 anni fa |
|
Alexey Parfenov
|
6123979952
server : allow to specify custom prompt for penalty calculation (#3727)
|
2 anni fa |
 MaggotHATE
|
52c8bc3cf3
sampling : custom samplers order (#4285)
|
2 anni fa |
 kalomaze
|
238657db23
samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)
|
2 anni fa |
|
Georgi Gerganov
|
d1031cf49c
sampling : refactor init to use llama_sampling_params (#3696)
|
2 anni fa |
|
Georgi Gerganov
|
0e89203b51
speculative : add tree-based sampling example (#3624)
|
2 anni fa |
 Kerfuffle
|
70c29da118
common : fix mirostat state when using multiple sequences (#3543)
|
2 anni fa |
