Commit Verlauf

Autor SHA1 Nachricht Datum
  Sigbjørn Skjæret c3a2624339 vocab : fix ugm tokenizer precision (#13743) vor 8 Monaten
  Johannes Gäßler ffd0eae60b CUDA: fix race condition in FA vector kernels (#13742) vor 8 Monaten
  Diego Devesa b775345d78 ci : enable winget package updates (#13734) vor 8 Monaten
  Diego Devesa a70a8a69c2 ci : add winget package updater (#13732) vor 8 Monaten
  Georgi Gerganov d13d0f6135 hparams : initialize arrays (#13728) vor 8 Monaten
  Xuan-Son Nguyen 8a2afb7520 llama : allow custom list of swa_layers (#13726) vor 8 Monaten
  Xuan-Son Nguyen 9ecf3e66a3 server : support audio input (#13714) vor 8 Monaten
  Chenguang Li faaaff5f94 CANN: Support MUL_MAT_ID for q8_0 and q4_0 (#13705) vor 8 Monaten
  Xuan-Son Nguyen e16c4731c7 ggml : fix the order of ggml_unary_op (#13718) vor 8 Monaten
  Jeff Bolz 1dcd01960c vulkan: support CPY from any type to itself (#13695) vor 8 Monaten
  Jeff Bolz c10ed6cbcc vulkan: Disable coopmat/coopmat2/bfloat extensions if glslc doesn't support it (#13696) vor 8 Monaten
  Judd a127ff1780 use LOG_WARN to replace `std::cerr` (#13657) vor 8 Monaten
  Diego Devesa 3079e9ac8e release : fix windows hip release (#13707) vor 8 Monaten
  Georgi Gerganov 8a1d206f1d tts : fix n_ubatch + make WavTokenizer cache-less (#13713) vor 8 Monaten
  Xuan-Son Nguyen 797990c4bc mtmd : add ultravox audio input (#13623) vor 8 Monaten
  Aaron Teo ab86335760 common: Include torch package for s390x (#13699) vor 8 Monaten
  Georgi Gerganov cc74d5be99 server : pad small embedding batches (#13692) vor 8 Monaten
  Sigbjørn Skjæret 5be24af73d gguf-py : correct charsmap parameter typing (#13701) vor 8 Monaten
  Nicolò Scipione d394a9aedc sycl : Remove waits from function calls (#13702) vor 8 Monaten
  Ewan Crawford 6b56a64690 SYCL: Avoid using with SYCL-Graph for unsupported nodes (#13587) vor 8 Monaten
  Henry Linjamäki a4e8912dfd opencl: Add support for multiple devices (#12622) vor 8 Monaten
  Henry Linjamäki edbf42edfd opencl: fix couple crashes (#12795) vor 8 Monaten
  Diego Devesa d643bb2c79 releases : build CPU backend separately (windows) (#13642) vor 8 Monaten
  Georgi Gerganov 8e186ef0e7 hparams : support models for which all layers use SWA (#13682) vor 8 Monaten
  Georgi Gerganov 5fbfe384d4 server : improve error reporting (#13680) vor 8 Monaten
  antichristHater c76532e7ba convert : add qwen2vl support for unsloth merges (#13686) vor 8 Monaten
  Sigbjørn Skjæret 2aa777d86d examples : switch retrieval to llama_encode (#13685) vor 8 Monaten
  Emmanuel Ferdman eb0f5c28d3 gguf-py : display the invalid gguf type (#13687) vor 8 Monaten
  Xuan-Son Nguyen cf4cb59e64 ggml : add ggml_gelu_erf() (#13667) vor 8 Monaten
  Robin Davidsson 0d5c742161 server : Add the endpoints /api/tags and /api/chat (#13659) vor 8 Monaten