]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-03-20 Georgi Gerganovai : limit runtime of the agent (#20816)
2026-03-20 James O'Learycommon : fix typo in debug log ('extracft' -> 'extract...
2026-03-20 Georgi Gerganovai : do not run bash commands in the prompt (#20810)
2026-03-20 Victor Villarmodel : fix Granite Hybrid type check for 7B.A1B (...
2026-03-20 Xuan-Son Nguyenserver: (doc) clarify in-scope and out-scope features...
2026-03-20 Jeff Bolzvulkan: change gated_delta_net to shard a column across...
2026-03-20 Ruikai Pengcontext: zero output buffer on allocation (#20781)
2026-03-20 Ruikai Pengmodel: assert nextn_predict_layers to prevent underflow...
2026-03-20 Georgi Gerganovserver : improve mtmd ctx checkpoints (#20726)
2026-03-20 hipuddingCANN: add BF16 support for core operators (#20152)
2026-03-20 Seyoung Jeongdocs : fix Metal backend op support status in ops.md...
2026-03-20 Georgi Gerganovai : update find-related action (#20790)
2026-03-20 Ruikai Pengjinja : fix heap OOB read in value equality comparison...
2026-03-20 James O'Learycommon/parser : fix out_of_range crash in throw path...
2026-03-19 Ben Racicotserver: fix router mode deadlock on child crash and...
2026-03-19 Tomeamisdocs: Update server README to reflect PR #20297 (#20560)
2026-03-19 Sundaram krishnanggml: guard KleidiAI DOWNLOAD_EXTRACT_TIMESTAMP for...
2026-03-19 Georgi Gerganovci : improve action for duplicate issue (#20772)
2026-03-19 Rail Chabdarovhip: Avoid compiler bug in RDNA code generation during...
2026-03-19 Ryan Gouldenserver: Add cached_tokens info to oaicompat responses...
2026-03-19 James O'Learychat : handle tool calls with no required args in TAG_W...
2026-03-19 Georgi Gerganovci : clarify gh command for viewing issues (#20766)
2026-03-19 Yiwei Shaohexagon: add Matrix Extensions (HMX) for Hexagon NPU...
2026-03-19 uvosci : add hip quality check (#20430)
2026-03-19 Piotr Wilkin... common/parser: add proper reasoning tag prefill reading...
2026-03-19 Reese Levineggml webgpu: ops support for qwen3.5 (SET, TRI_SOLVE...
2026-03-19 ddh0common : add LLAMA_ARG_SPEC_TYPE (#20744)
2026-03-19 Georgi Gerganovci : add action for finding duplicate issues (#20756)
2026-03-19 PascalServer becomes the source of truth for sampling paramet...
2026-03-19 Xuan-Son Nguyenmtmd: add clip_graph::build_mm() (#20751)
2026-03-19 PascalWebUI: Persist the on/off state of the MCP servers...
2026-03-19 Aleksander... webui: Improve model parsing logic + add unit tests...
2026-03-19 Dowonconvert : support is_causal hyperparameter (#20746)
2026-03-19 Aldehir Rojascommon : fix gpt-oss content removal (#20745)
2026-03-19 Evevulkan: dequantize iq4_xs 4 at a time (#20657)
2026-03-19 Charles Xucmake : fix build warning when kleidiai is enabled...
2026-03-19 Sigbjørn Skjæretvocab : assert array size of scores and toktypes (...
2026-03-19 Kevin Hannondocs: add information about openvino in the docker...
2026-03-19 Chenguang LiCANN: handle in-place ROPE on non-contiguous f32 tensor...
2026-03-19 Masashi Yoshimuraggml-webgpu: Update the `RMS_NORM` preprocessor and...
2026-03-19 Masashi Yoshimuraggml-webgpu: Add supports for `DIAG` and `TRI` (#20664)
2026-03-19 Chenguang LiCANN: support flash attention for head dim not multiple...
2026-03-18 Michael Graumodel : add control vector support where missing (...
2026-03-18 Sigbjørn Skjæretgguf-py : cleaner way to get the first key (#20727)
2026-03-18 crsawyerRebuild index.html.gz (#20724)
2026-03-18 Reese LevineMove to no timeout for WaitAny in graph submission...
2026-03-18 Shaw Nguyenggml-cpu/x86: fix unused changemask warning in repack...
2026-03-18 Georgi Gerganovsync : ggml
2026-03-18 Georgi Gerganovggml : bump version to 0.9.8 (ggml/1442)
2026-03-18 Georgi Gerganovggml : restore ggml_type_sizef() to aboid major version...
2026-03-18 Julien Chaumondwebui: improve tooltip wording for attachment requireme...
2026-03-18 Pop Flamingollama : re-enable manual LoRA adapter free (#19983)
2026-03-18 Masato Nakasakatests : fix test-jinja-py Windows failures by bypassing...
2026-03-18 Aldehir Rojascommon : rework gpt-oss parser (#20393)
2026-03-18 Aaron Teotests: enable kv_unified to prevent cuda oom error...
2026-03-18 Aleksander... webui: Fix duplicated messages on q param (#20715)
2026-03-18 uvosHIP : ignore return of hipMemAdvise [no ci] (#20696)
2026-03-18 Andreas Obersteinercontext : fix graph not resetting when control vector...
2026-03-17 Krishna Sridharhexagon: add neg, exp, sigmoid, softplus ops, cont...
2026-03-17 Ruben Ortlamvulkan: disable mmvq on Intel Windows driver (#20672)
2026-03-17 Kevin Hannonggml-blas: set mkl threads from thread context (#20602)
2026-03-17 Piotr Wilkin... common/parser: add `--skip-chat-parsing` to force a...
2026-03-17 Taimur Ahmadggml-cpu: fix RVV checks in quants and repacking (...
2026-03-17 Sigbjørn Skjæretci : bump ccache [no ci] (#20679)
2026-03-17 Ruben Ortlamvulkan: async and event fixes (#20518)
2026-03-17 Georgi Gerganovserver : fix ctx checkpoint invalidation (#20671)
2026-03-17 Justin Bradfordkleidiai : fix MUL_MAT support for batched (3D) inputs...
2026-03-17 Ruben Ortlamvulkan: allow graphics queue only through env var ...
2026-03-17 Neo Zhang[SYCL] ehance UPSCALE to support all UT cases (#20637)
2026-03-17 Piotr Wilkin... tools/server: support refusal content for Responses...
2026-03-16 Xuan-Son Nguyenmodel: mistral small 4 support (#20649)
2026-03-16 Georgi Gerganovci : disable AMX jobs (#20654)
2026-03-16 Georgi Gerganovbenches : add Nemotron 3 Nano on DGX Spark (#20652)
2026-03-16 Sigbjørn Skjærettests : write to binary buffer to avoid newline transla...
2026-03-16 Martin Klacerkleidiai: add data type check to get_tensor_traits...
2026-03-16 Sigbjørn Skjæretci : update labeler (#20629)
2026-03-16 Aldehir Rojasjinja : add capability check for object args (#20612)
2026-03-16 Georgi Gerganovsync : ggml
2026-03-16 Georgi Gerganovggml : try fix arm build (whisper/0)
2026-03-16 David366AIggml : extend im2col f16 (ggml/1434)
2026-03-16 Pascalwebui: add model information dialog to router mode...
2026-03-16 Aman Guptallama-graph: replace cont with reshape for alpha in...
2026-03-16 Aleksander... webui: Add MCP CORS Proxy detection logic & UI (#20167)
2026-03-16 PascalFix model selector locked to first loaded model with...
2026-03-16 Woof Dogwebui: use date in more human readable exported filenam...
2026-03-16 Ruben Ortlamvulkan: fix flash attention dot product precision ...
2026-03-16 Sigbjørn Skjæretmodel : wire up Nemotron-H tensors for NVFP4 support...
2026-03-16 Richard Davisonconvert : support mixed-precision ModelOpt models with...
2026-03-16 Masato Nakasakacommon : fix iterator::end() dereference (#20445)
2026-03-16 Aman GuptaCUDA: GDN hide memory latency (#20537)
2026-03-15 Piotr Wilkin... tools/cli: fix disable reasoning (#20606)
2026-03-15 Georgi Gerganovserver : fix wait in test_cancel_requests() test (...
2026-03-15 Sigbjørn Skjæretsycl : fix for untransposed GDA recurrent state (#20583)
2026-03-15 Sigbjørn Skjæretci : only save openvino caches on github-hosted master...
2026-03-15 Johannes GäßlerCUDA: limit number of FA stream-k CUDA blocks (#20586)
2026-03-15 Pascalggml: avoid creating CUDA context during device init...
2026-03-15 Adrien Gallouëtvendor : update cpp-httplib to 0.38.0 (#20578)
2026-03-15 MoonShadow ggml/hip: fix APU compatibility - soft error handling...
2026-03-15 Eric Hsiehfix: prevent nullptr dereference (#20552)
2026-03-15 Sigbjørn Skjæretcodeowners : use teams (#20526)
next