Commit Verlauf

Autor SHA1 Nachricht Datum
  davidef d1d8241600 server : fix incoming tasks not process in order (#15395) vor 5 Monaten
  Dobri Danchev 618575c582 Fix broken build: require updated pip to support --break-system-packages (#15357) vor 5 Monaten
  compilade f44f793172 ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors (#15379) vor 5 Monaten
  Jeff Bolz ae532eac2c vulkan: disable spirv-opt for bfloat16 shaders (#15352) vor 5 Monaten
  Oleksandr Kuvshynov e5155e6986 server : export max observed n_past value (#15361) vor 5 Monaten
  Jeff Bolz 21c17b5bef vulkan: Use larger workgroups for mul_mat_vec when M is small (#15355) vor 5 Monaten
  Dong Won Kim 19f4decae0 vulkan: support sqrt (#15370) vor 5 Monaten
  Sigbjørn Skjæret 4d196981d4 convert : force patch_embd weights to F16 or F32 to avoid broken GGUFs (#15367) vor 5 Monaten
  Sigbjørn Skjæret b143fbc87a ci : fix hang in windows-hip build/release (#15365) vor 5 Monaten
  Jeff Bolz de5627910d vulkan: Optimize argsort (#15354) vor 5 Monaten
  Tarek Dakhran 65349f26f2 model : support vision LiquidAI LFM2-VL family (#15347) vor 5 Monaten
  Jeff Bolz 1fe00296f5 vulkan: fuse adds (#15252) vor 5 Monaten
  Jeff Bolz de2192794f vulkan: Support mul_mat_id with f32 accumulators (#15337) vor 5 Monaten
  Jeff Bolz 2e2b22ba66 vulkan: Add missing bounds checking to scalar/coopmat1 mul_mat_id (#15334) vor 5 Monaten
  rmatif 912ff8c119 OpenCL: add initial FA support (#14987) vor 5 Monaten
  Daniel Bevenius 5e6229a840 common : fix double bos, use common_chat_templates for add_bos and add_eos (#15326) vor 5 Monaten
  lhez e2c1bfff53 opencl: add initial mxfp4 support via mv (#15270) vor 5 Monaten
  Georgi Gerganov 5edf1592fd vulkan : fix out-of-bounds access in argmax kernel (#15342) vor 5 Monaten
  Georgi Gerganov db3010bd23 vulkan : fix compile warnings on macos (#15340) vor 5 Monaten
  Aaron Teo ff27f80a74 ggml: initial IBM zDNN backend (#14975) vor 5 Monaten
  Sigbjørn Skjæret d3248d9b65 ci : fix ios-xcode-build (#15324) vor 5 Monaten
  Diego Devesa 7aeee88cfe ci : move ccache action to ggml-org fork (#15328) vor 5 Monaten
  Johannes Gäßler b07791aa1d test-opt: fix backend support check (#15317) vor 5 Monaten
  Johannes Gäßler 4227c9be42 CUDA: fix negative KV_max values in FA (#15321) vor 5 Monaten
  Georgi Gerganov df36bce667 eval-callback : stop on first NaN (#15320) vor 5 Monaten
  Diego Devesa f75b830647 chat : include kwargs in template example (#15309) vor 5 Monaten
  Daniel Bevenius 7a0de96045 llama : add 18-layer model type for Gemma 3-270m (#15319) vor 5 Monaten
  simevo e4e915912c devops : fix compile bug when the BASE_CUDA_DEV_CONTAINER is based on Ubuntu 24.04 (#15005) vor 5 Monaten
  uvos 5ba36f6103 HIP: Cleanup hipification header (#15285) vor 5 Monaten
  Aldehir Rojas b204a5a234 gpt-oss: implement harmony parsing (#15181) vor 5 Monaten