Xuan Son Nguyen 958367bf53 server : refactor slot input data, move tokenizer to HTTP thread (#10023) пре 1 година
..
steps 958367bf53 server : refactor slot input data, move tokenizer to HTTP thread (#10023) пре 1 година
ctx_shift.feature 1bde94dd02 server : remove self-extend features (#9860) пре 1 година
embeddings.feature f4d2b8846a llama : add reranking support (#9510) пре 1 година
environment.py bd60d82d0c server tests : more pythonic process management; fix bare `except:` (#6146) пре 1 година
infill.feature 958367bf53 server : refactor slot input data, move tokenizer to HTTP thread (#10023) пре 1 година
issues.feature 9731134296 server: tests: passkey challenge / self-extend with context shift demo (#5832) пре 1 година
lora.feature 1e6f6554aa server : add lora hotswap endpoint (WIP) (#8857) пре 1 година
parallel.feature 9b2c24c099 server : simplify state machine for slot (#9283) пре 1 година
passkey.feature 9b2c24c099 server : simplify state machine for slot (#9283) пре 1 година
rerank.feature f4d2b8846a llama : add reranking support (#9510) пре 1 година
results.feature 3bc10cb485 server : fix temperature + disable some tests (#7409) пре 1 година
security.feature 458367a906 server : better security control for public deployments (#9776) пре 1 година
server.feature 78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108) пре 1 година
slotsave.feature d7e852c1bc Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425) пре 1 година
wrong_usages.feature 6e7d133a5f server : refactor multitask handling (#9274) пре 1 година