Move vars to dynamic, add metrics (#1085) 98b1c51 unverified nsarrazin HF staff rtrm HF staff victor HF staff commited on May 3
Expose sampling controls in assistants (#955) (#959) d4016bc unverified nsarrazin HF staff victor HF staff Mishig commited on Mar 27
Fix prompt caching on llama.cpp endpoints (#920) eb071be unverified reversebias nsarrazin HF staff commited on Mar 11
Fix issue with "continue" feature on llama.cpp endpoints (#898) 714ff2c unverified nsarrazin HF staff commited on Mar 5
Bug Fix: Json Decoder aggessively pulls json (#867) 9c5a826 unverified Matthew Current nsarrazin HF staff commited on Mar 5
Conversation trees (#223) (#807) e6addfc unverified nsarrazin HF staff victor HF staff commited on Feb 15
Standardize HF_ACCESS_TOKEN -> HF_TOKEN (#610) 3cbea34 unverified Wauplin HF staff nsarrazin HF staff commited on Dec 6, 2023
Add support for passing an API key or any other custom token in the authorization header (#579) a1afcb6 unverified Galén nsarrazin HF staff commited on Dec 5, 2023
Modular backends & support for openAI & AWS endpoints (#541) 9db8ced unverified nsarrazin HF staff chenhunghan Henry Chen Mishig coyotte508 HF staff commited on Nov 15, 2023
