コミット履歴

作者 SHA1 メッセージ 日付
  Henry Linjamäki a4e8912dfd opencl: Add support for multiple devices (#12622) 8 ヶ月 前
  Henry Linjamäki edbf42edfd opencl: fix couple crashes (#12795) 8 ヶ月 前
  Diego Devesa d643bb2c79 releases : build CPU backend separately (windows) (#13642) 8 ヶ月 前
  Georgi Gerganov 8e186ef0e7 hparams : support models for which all layers use SWA (#13682) 8 ヶ月 前
  Georgi Gerganov 5fbfe384d4 server : improve error reporting (#13680) 8 ヶ月 前
  antichristHater c76532e7ba convert : add qwen2vl support for unsloth merges (#13686) 8 ヶ月 前
  Sigbjørn Skjæret 2aa777d86d examples : switch retrieval to llama_encode (#13685) 8 ヶ月 前
  Emmanuel Ferdman eb0f5c28d3 gguf-py : display the invalid gguf type (#13687) 8 ヶ月 前
  Xuan-Son Nguyen cf4cb59e64 ggml : add ggml_gelu_erf() (#13667) 8 ヶ月 前
  Robin Davidsson 0d5c742161 server : Add the endpoints /api/tags and /api/chat (#13659) 8 ヶ月 前
  Dorin-Andrei Geman 42158ae2e8 server : fix first message identification (#13634) 8 ヶ月 前
  Georgi Gerganov 797f2ac062 kv-cache : simplify the interface (#13660) 8 ヶ月 前
  Georgi Gerganov b44890df2e model : disable SWA for Phi models (#13676) 8 ヶ月 前
  R0CKSTAR 33983057d0 musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647) 8 ヶ月 前
  Eve fb1cab201c vulkan: fix warnings (#13626) 8 ヶ月 前
  l3utterfly b7a17463ec mtmd-helper : bug fix to token batching in mtmd (#13650) 8 ヶ月 前
  Georgi Gerganov be0239693c model : fix llama4 graph (#13663) 8 ヶ月 前
  Georgi Gerganov a4090d1174 llama : remove llama_kv_cache_view API + remove deprecated (#13653) 8 ヶ月 前
  Johannes Gäßler b69f1647f9 CUDA: skip fully masked-out KV in FA vec kernel (#13584) 8 ヶ月 前
  Sigbjørn Skjæret 759e37b0d8 tests : avoid github urls due to throttling (#13654) 8 ヶ月 前
  Svetlozar Georgiev 4245e622e0 sycl: disable reorder for sycl mulmat (#13536) 8 ヶ月 前
  0cc4m c9c64dee57 Set GLM4 blk.*.attn_output.weight, kqv_out-* matmul to GGML_PREC_F32 to fix infinity values in output (#13639) 8 ヶ月 前
  Georgi Gerganov c00a2634be metal : fix typo in FA kernel comments (#13651) 8 ヶ月 前
  Georgi Gerganov e298d2fbd0 kv-cache : add SWA support (#13194) 8 ヶ月 前
  Xinpeng Dou f0adb80bf7 CANN: Update CANN model support (#13162) 8 ヶ月 前
  Nicolò Scipione f7c9429c85 sycl : Overcoming workaround for mmap() allocation on Windows (#13482) 8 ヶ月 前
  psocolovsky 1dfbf2cf3a common : add load_progress_callback (#13617) 8 ヶ月 前
  0cc4m 8960efd0a6 Vulkan: Add f32 accumulator support to quantized mul mat to fix GLM4 32B incoherence (#13607) 8 ヶ月 前
  Alberto Cabrera Pérez 725f23f1f3 sycl : backend documentation review (#13544) 8 ヶ月 前
  Xuan-Son Nguyen 92ecdcc06a mtmd : add vision support for llama 4 (#13282) 8 ヶ月 前