Commit History

Автор SHA1 Съобщение Дата
  matteo caf5681fcb server : support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client (#13196) преди 6 месеца
  Sigbjørn Skjæret 88fc854b4b llama : improve sep token handling (#14272) преди 7 месеца
  aa956 d67341dc18 server : add server parameters for draft model cache type (#13782) преди 7 месеца
  Georgi Gerganov d3e64b9f49 llama : rework embeddings logic (#14208) преди 7 месеца
  Olivier Chafik c9bbc77931 `server`: update deepseek reasoning format (pass reasoning_content as diffs) (#13933) преди 7 месеца
  Max Krasnyansky 053b1539c0 threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (#12995) преди 7 месеца
  Georgi Gerganov 53f925074d sync : vendor (#13901) преди 7 месеца
  Olivier Chafik cdf94a1802 server: --offline mode (#13804) преди 7 месеца
  Olivier Chafik e121edc432 `server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771) преди 7 месеца
  Xuan-Son Nguyen 797990c4bc mtmd : add ultravox audio input (#13623) преди 8 месеца
  Sigbjørn Skjæret 2aa777d86d examples : switch retrieval to llama_encode (#13685) преди 8 месеца
  Georgi Gerganov a4090d1174 llama : remove llama_kv_cache_view API + remove deprecated (#13653) преди 8 месеца
  Georgi Gerganov e298d2fbd0 kv-cache : add SWA support (#13194) преди 8 месеца
  Isaac McFadyen 6a2bc8bfb7 server : added --no-prefill-assistant flag (#13608) преди 8 месеца
  Georgi Gerganov 518329b2d4 parallel : add option for non-shared and larger prompts (#13598) преди 8 месеца
  David Huang 7f323a589f Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386) преди 8 месеца
  Xuan-Son Nguyen 7fef11766c arg : add env var to control mmproj (#13416) преди 8 месеца
  Xuan-Son Nguyen 33eff40240 server : vision support via libmtmd (#12898) преди 8 месеца
  Bartowski efb8b47eda imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389) преди 8 месеца
  Georgi Gerganov 51fb96b1ff context : remove logits_all flag (#13284) преди 8 месеца
  Georgi Gerganov 4773d7a02f examples : remove infill (#13283) преди 8 месеца
  Xuan-Son Nguyen 9b61acf060 mtmd : rename llava directory to mtmd (#13311) преди 8 месеца
  Diego Devesa 1d36b3670b llama : move end-user examples to tools directory (#13249) преди 8 месеца
  Georgi Gerganov fab647e884 server : add cache reuse card link to help (#13230) преди 8 месеца
  Xuan-Son Nguyen 13c9a3319b arg : remove CURLINFO_EFFECTIVE_METHOD (#13228) преди 8 месеца
  Xuan-Son Nguyen 6f67cf1f48 arg : -hf do not fail if url mismatch (#13219) преди 8 месеца
  Olivier Chafik 3b127c7385 common : add -jf / --json-schema-file flag (#12011) преди 8 месеца
  Xuan-Son Nguyen 5933e6fdc9 arg : allow using -hf offline (#13202) преди 8 месеца
  Georgi Gerganov 43f2b07193 common : fix noreturn compile warning (#13151) преди 8 месеца
  Xuan-Son Nguyen 85f36e5e71 arg : fix unused variable (#13142) преди 8 месеца