 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 |
 g2mt
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
5 mesi fa |
|
Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
7 mesi fa |
|
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 mesi fa |
 mgroeber9110
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
10 mesi fa |
|
Georgi Gerganov
|
abd4d0bc4f
speculative : update default params (#11954)
|
11 mesi fa |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 anno fa |
|
Georgi Gerganov
|
c2a16c0bdb
server : fix free of spec context and batch (#10651)
|
1 anno fa |
|
Georgi Gerganov
|
9fd8c2687f
server : add more information about error (#10455)
|
1 anno fa |
|
Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
1 anno fa |
