 Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
1 год назад |
 Xuan Son Nguyen
|
9b2c24c099
server : simplify state machine for slot (#9283)
|
1 год назад |
|
Xuan Son Nguyen
|
4a1411b4f1
server : fix missing lock (#9334)
|
1 год назад |
|
Xuan Son Nguyen
|
6e7d133a5f
server : refactor multitask handling (#9274)
|
1 год назад |
 Faisal Zaghloul
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 год назад |
 Jan Boon
|
9f7d4bcf5c
server : fix crash when error handler dumps invalid utf-8 json (#9195)
|
1 год назад |
|
Xuan Son Nguyen
|
fc54ef0d1c
server : support reading arguments from environment variables (#9105)
|
1 год назад |
|
Xuan Son Nguyen
|
8b3befc0e2
server : refactor middleware and /health endpoint (#9056)
|
1 год назад |
 Riceball LEE
|
37501d9c79
server : fix duplicated n_predict key in the generation_settings (#8994)
|
1 год назад |
 Zhenwei Jin
|
4af8420afb
common : remove duplicate function llama_should_add_bos_token (#8778)
|
1 год назад |
 Jiří Podivín
|
234b30676a
server : init stop and error fields of the result struct (#9026)
|
1 год назад |
 compilade
|
98a532d474
server : fix segfault on long system prompt (#8987)
|
1 год назад |
|
Georgi Gerganov
|
5ef07e25ac
server : handle models with missing EOS token (#8997)
|
1 год назад |
 Mathieu Geli
|
daef3ab233
server : add one level list nesting for embeddings (#8936)
|
1 год назад |
|
Xuan Son Nguyen
|
1e6f6554aa
server : add lora hotswap endpoint (WIP) (#8857)
|
1 год назад |
 Liu Jia
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
1 год назад |
 ardfork
|
978ba3d83d
Server: Don't ignore llama.cpp params (#8754)
|
1 год назад |
 RunningLeon
|
3807c3de04
server : respect `--special` cli arg (#8553)
|
1 год назад |
 Douglas Hanley
|
c3ebcfa148
server : ensure batches are either all embed or all completion (#8420)
|
1 год назад |
 Clint Herron
|
278d0e1846
Initialize default slot sampling parameters from the global context. (#8418)
|
1 год назад |
|
Clint Herron
|
a59f8fdc85
Server: Enable setting default sampling parameters via command-line (#8402)
|
1 год назад |
 Bjarke Viksøe
|
cb4d86c4d7
server: Retrieve prompt template in /props (#8337)
|
1 год назад |
 Sigbjørn Skjæret
|
38373cfbab
Add SPM infill support (#8016)
|
1 год назад |
|
Xuan Son Nguyen
|
48e6b92cc3
Add chat template support for llama-cli (#8068)
|
1 год назад |
 sasha0552
|
ba58993152
server : fix smart slot selection (#8020)
|
1 год назад |
|
Sigbjørn Skjæret
|
91c188d6c2
Only use FIM middle token if it exists (#7648)
|
1 год назад |
|
Georgi Gerganov
|
704a35b183
server : restore numeric prompts (#7883)
|
1 год назад |
|
Georgi Gerganov
|
d9da0e4986
server : improve "prompt" handling (#7847)
|
1 год назад |
|
sasha0552
|
7a16ce7db2
server : smart slot selection using Longest Common Prefix (#7728)
|
1 год назад |
 woodx
|
a5cabd7649
server : do not get prompt in infill mode (#7286)
|
1 год назад |
