Cronologia Commit

Autore SHA1 Messaggio Data
  Georgi Gerganov b141e5f6ef server : enable KV cache defrag by default (#10233) 1 anno fa
  Xuan Son Nguyen a71d81cf8c server : revamp chat UI with vuejs and daisyui (#10175) 1 anno fa
  Xuan Son Nguyen 9e0ecfb697 server : clarify /slots endpoint, add is_processing (#10162) 1 anno fa
  Georgi Gerganov 8d8ff71536 llama : remove Tail-Free sampling (#10071) 1 anno fa
  wwoodsTM ff252ea48e llama : add DRY sampler (#9702) 1 anno fa
  Xuan Son Nguyen 958367bf53 server : refactor slot input data, move tokenizer to HTTP thread (#10023) 1 anno fa
  Georgi Gerganov 8901755ba3 server : add n_indent parameter for line indentation requirement (#9929) 1 anno fa
  Georgi Gerganov 223c25a72f server : improve infill context reuse (#9894) 1 anno fa
  Georgi Gerganov d4c19c0f5c server : accept extra_context for the infill endpoint (#9874) 1 anno fa
  Georgi Gerganov c7181bd294 server : reuse cached context chunks (#9866) 1 anno fa
  Georgi Gerganov edc265661c server : add option to time limit the generation phase (#9865) 1 anno fa
  Georgi Gerganov 1bde94dd02 server : remove self-extend features (#9860) 1 anno fa
  Georgi Gerganov 95c76e8e92 server : remove legacy system_prompt feature (#9857) 1 anno fa
  Georgi Gerganov 11ac9800af llama : improve infill support and special token detection (#9798) 1 anno fa
  Xuan Son Nguyen 458367a906 server : better security control for public deployments (#9776) 1 anno fa
  Daniel Kleine 133c7b46b3 Fixed RNG seed docs (#9723) 1 anno fa
  Georgi Gerganov f4d2b8846a llama : add reranking support (#9510) 1 anno fa
  Xuan Son Nguyen afbbfaa537 server : add more env vars, improve gen-docs (#9635) 1 anno fa
  Xuan Son Nguyen 0b3bf966f4 server : add --no-context-shift option (#9607) 1 anno fa
  Vinesh Janarthanan 8a308354f6 server : match OAI structured output response (#9527) 1 anno fa
  Bert Wagner 8b836ae731 arg : add env variable for parallel (#9513) 1 anno fa
  Georgi Gerganov 6262d13e0b common : reimplement logging (#9418) 1 anno fa
  Mathijs Henquet 78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108) 1 anno fa
  Xuan Son Nguyen bfe76d4a17 common : move arg parser code to `arg.cpp` (#9388) 1 anno fa
  Xuan Son Nguyen 1b9ae5189c common : refactor arg parser (#9308) 1 anno fa
  Georgi Gerganov df270ef745 llama : refactor sampling v2 (#9294) 1 anno fa
  Xuan Son Nguyen a77feb5d71 server : add some missing env variables (#9116) 1 anno fa
  Xuan Son Nguyen fc54ef0d1c server : support reading arguments from environment variables (#9105) 1 anno fa
  Xuan Son Nguyen 8b3befc0e2 server : refactor middleware and /health endpoint (#9056) 1 anno fa
  Xuan Son Nguyen 1e6f6554aa server : add lora hotswap endpoint (WIP) (#8857) 1 anno fa