История коммитов

Автор SHA1 Сообщение Дата
  Georgi Gerganov e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 10 месяцев назад
  Ishaan Gandhi 2048b5913d server : fix crash when using verbose output with input tokens that are not in printable range (#12178) (#12338) 10 месяцев назад
  Olivier Chafik be421fc429 `tool-call`: ensure there's always a non-empty tool call id (#12292) 10 месяцев назад
  Olivier Chafik 2b3a25c212 `sampler`: fixes trigger tokens + lazy grammars (fix typo cast from token to string) (#12291) 10 месяцев назад
  Georgi Gerganov 7ab364390f server : infill gen ends on new line (#12254) 10 месяцев назад
  Sigbjørn Skjæret 8fad3c7a7c server : Log original chat template parsing error (#12233) 10 месяцев назад
  Olivier Chafik 669912d9a5 `tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034) 10 месяцев назад
  Clauszy 06a92a193a server : fix cache reuse logic (#12161) 10 месяцев назад
  Georgi Gerganov abd4d0bc4f speculative : update default params (#11954) 11 месяцев назад
  Olivier Chafik 63e489c025 tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900) 11 месяцев назад
  Xuan-Son Nguyen 63ac128563 server : add TEI API format for /rerank endpoint (#11942) 11 месяцев назад
  Antoine Viallon c4d29baf32 server : fix divide-by-zero in metrics reporting (#11915) 11 месяцев назад
  Georgi Gerganov 68ff663a04 repo : update links to new url (#11886) 11 месяцев назад
  Olivier Chafik c7f460ab88 `server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607) 11 месяцев назад
  Oleksandr Kuvshynov e4376270d9 llama.cpp: fix warning message (#11839) 11 месяцев назад
  Daniel Bevenius a18f481f99 server : use common_token_to_piece instead of common_detokenize (#11740) 11 месяцев назад
  Xuan-Son Nguyen 0893e0114e server : correct signal handler (#11795) 11 месяцев назад
  Xuan-Son Nguyen 55ac8c7791 server : (webui) revamp Settings dialog, add Pyodide interpreter (#11759) 11 месяцев назад
  Georgi Gerganov aaa5505307 server : minor log updates (#11760) 11 месяцев назад
  Xuan-Son Nguyen 3962fc1a79 server : add try..catch to places not covered by set_exception_handler (#11620) 11 месяцев назад
  Olivier Chafik bfcce4d693 `tool-call`: support Command R7B (+ return tool_plan "thoughts" in API) (#11585) 11 месяцев назад
  Olivier Chafik a83f528688 `tool-call`: fix llama 3.x and functionary 3.2, play nice w/ pydantic_ai package, update readme (#11539) 11 месяцев назад
  Olivier Chafik 5783575c9d Fix chatml fallback for unsupported builtin templates (when --jinja not enabled) (#11533) 11 месяцев назад
  Daniel Bevenius a2df2787b3 server : update help metrics processing/deferred (#11512) 11 месяцев назад
  Olivier Chafik 8b576b6c55 Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639) 11 месяцев назад
  Daniel Bevenius 4314e56c4f server : use lambda instead of std::bind (#11507) 11 месяцев назад
  Nigel Bosch eb7cf15a80 server : add /apply-template endpoint for additional use cases of Minja functionality (#11489) 11 месяцев назад
  Daniel Bevenius e51c47b401 server : update auto gen files comments [no ci] (#11484) 11 месяцев назад
  Xuan Son Nguyen 49b0e3cec4 server : fix cleaning up stream task (#11418) 11 месяцев назад
  Xuan Son Nguyen 5845661640 server : add more clean up when cancel_tasks is called (#11340) 11 месяцев назад