Commit Verlauf

Autor SHA1 Nachricht Datum
  matteo caf5681fcb server : support jinja extra template kwargs (Qwen3 enable_thinking feature), from command line and from client (#13196) vor 6 Monaten
  Georgi Gerganov 7b50d589a8 kv-cells : fix tracking of seq_pos (#14339) vor 7 Monaten
  Georgi Gerganov 4c9fdfbe15 ubatch : new splitting logic (#14217) vor 7 Monaten
  aa956 d67341dc18 server : add server parameters for draft model cache type (#13782) vor 7 Monaten
  Georgi Gerganov 89fea80d29 server : fix incorrect usage of llama_get_embeddings() (#14225) vor 7 Monaten
  Georgi Gerganov d3e64b9f49 llama : rework embeddings logic (#14208) vor 7 Monaten
  Eric Curtin cd355eda7d server : When listening on a unix domain socket don't print http:// and port (#14180) vor 7 Monaten
  Georgi Gerganov ffad043973 server : fix SWA condition for full context reprocess (#14163) vor 7 Monaten
  Georgi Gerganov 7d516443dd server : re-enable SWA speculative decoding (#14131) vor 7 Monaten
  Taylor 2baf07727f server : pass default --keep argument (#14120) vor 7 Monaten
  Juk Armstrong 3a12db23b6 Fixed spec timings to: accepted/tested instead of accepted/drafted (#14104) vor 7 Monaten
  Georgi Gerganov 87d34b381d server : fix LRU check (#14079) vor 7 Monaten
  Georgi Gerganov 745aa5319b llama : deprecate llama_kv_self_ API (#14030) vor 7 Monaten
  Georgi Gerganov 3637576288 server : disable speculative decoding for SWA models (#13970) vor 7 Monaten
  Olivier Chafik c9bbc77931 `server`: update deepseek reasoning format (pass reasoning_content as diffs) (#13933) vor 7 Monaten
  Georgi Gerganov 3600cc2886 llama : use n_swa + n_ubatch cells for SWA cache (#13833) vor 7 Monaten
  Georgi Gerganov 3f55f781f1 llama : auto-batch preparation (#13845) vor 7 Monaten
  Georgi Gerganov 12d0188c0d kv-cache : refactor + add llama_memory_state_i (#13746) vor 7 Monaten
  Georgi Gerganov 53f925074d sync : vendor (#13901) vor 7 Monaten
  Xuan-Son Nguyen 10961339b2 mtmd : move helpers to dedicated library (⚠️ breaking change) (#13866) vor 7 Monaten
  Olivier Chafik 03f582ae8f server: fix streaming crashes (#13786) vor 7 Monaten
  Georgi Gerganov 79c137f776 examples : allow extracting embeddings from decoder contexts (#13797) vor 7 Monaten
  Olivier Chafik e121edc432 `server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771) vor 7 Monaten
  Olivier Chafik f5cd27b71d `server`: streaming of tool calls and thoughts when `--jinja` is on (#12379) vor 8 Monaten
  Xuan-Son Nguyen 9ecf3e66a3 server : support audio input (#13714) vor 8 Monaten
  Georgi Gerganov cc74d5be99 server : pad small embedding batches (#13692) vor 8 Monaten
  Georgi Gerganov 5fbfe384d4 server : improve error reporting (#13680) vor 8 Monaten
  Robin Davidsson 0d5c742161 server : Add the endpoints /api/tags and /api/chat (#13659) vor 8 Monaten
  Dorin-Andrei Geman 42158ae2e8 server : fix first message identification (#13634) vor 8 Monaten
  Georgi Gerganov 797f2ac062 kv-cache : simplify the interface (#13660) vor 8 Monaten