Commit History

Auteur SHA1 Bericht Datum
  Ervin Áron Tasnádi 0d3984424f ggml-vulkan: adds support for op CONV_TRANSPOSE_1D (#13813) 7 maanden geleden
  Georgi Gerganov 3e63a58ef7 kv-cache : refactor the update/defrag mechanism (#13988) 7 maanden geleden
  Diego Devesa 2589ad3704 ci : remove cuda 11.7 releases, switch runner to windows 2022 (#13997) 7 maanden geleden
  Diego Devesa 482548716f releases : use dl backend for linux release, remove arm64 linux release (#13996) 7 maanden geleden
  Xuan-Son Nguyen 3ac67535c8 llama-graph : use ggml_repeat_4d (#13998) 7 maanden geleden
  Johannes Gäßler 0b4be4c435 CUDA: fix FTZ in FA for Gemma 3 (#13991) 7 maanden geleden
  Georgi Gerganov e0e806f52e kv-cache : fix unified::seq_rm to work with seq_id < 0 (#13985) 7 maanden geleden
  Jeff Bolz 7e00e60ef8 vulkan: fix warnings in perf logger querypool code (#13937) 7 maanden geleden
  Xuan-Son Nguyen ea1431b0fa docs : add "Quick start" section for new users (#13862) 7 maanden geleden
  lhez 71e74a3ac9 opencl: add `backend_synchronize` (#13939) 7 maanden geleden
  rmatif bfb1e012a0 OpenCL: Add concat, tsembd, upscale, tanh, pad and repeat (#13840) 7 maanden geleden
  Georgi Gerganov 3637576288 server : disable speculative decoding for SWA models (#13970) 7 maanden geleden
  Georgi Gerganov ea394d7ab1 metal : use F32 accumulators in FA kernels (#13975) 7 maanden geleden
  Georgi Gerganov 5582c49c39 gemma : more consistent attention scaling for v2 and v3 (#13951) 7 maanden geleden
  Olivier Chafik c9bbc77931 `server`: update deepseek reasoning format (pass reasoning_content as diffs) (#13933) 7 maanden geleden
  Xuan-Son Nguyen bfd322796c mtmd : fix memory leak in mtmd_helper_eval_chunk_single (#13961) 7 maanden geleden
  shalinib-ibm 093e3f1feb cmake : Handle mixed-case 'Power' strings in POWER CPU detection (#13966) 7 maanden geleden
  Atharva Dubey 663445b0de sycl: quantize and reorder the input to q8_1 when reorder is enabled (#13826) 7 maanden geleden
  Johannes Gäßler 7675c555a1 gguf: fix failure on version == 0 (#13956) 7 maanden geleden
  Sigbjørn Skjæret 5e1c3aed40 convert : fix nomic-bert-moe mask token (#13757) 7 maanden geleden
  Sigbjørn Skjæret c496fe0b1d convert : fix vocab padding code for bert models (#13954) 7 maanden geleden
  Aaron Teo e57bb87ced ggml: check if non-native endian model is being loaded (#13943) 7 maanden geleden
  Georgi Gerganov f3a4b1659c sync : ggml 7 maanden geleden
  Kai Pastor 108009f5c7 vulkan : Remove unexpected ; (ggml/1253) 7 maanden geleden
  Kai Pastor d337252acf cmake : Fix broken CMake error messages (ggml/1252) 7 maanden geleden
  Radoslav Gerganov af6f91db47 ggml : remove ggml_graph_import and ggml_graph_export declarations (ggml/1247) 7 maanden geleden
  Georgi Gerganov a7b8d35f78 sync : whisper.cpp (ggml/1250) 7 maanden geleden
  Radoslav Gerganov 6eba72b71c ggml : install dynamic backends (ggml/1240) 7 maanden geleden
  Daniel Tang fedf034a98 ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 8 maanden geleden
  ddh0 8726392d3d readme : update bindings (#13950) 7 maanden geleden