]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-04-14 Yiwei Shaohexagon: optimization for HMX mat_mul (#21554)
2026-04-14 Xuan-Son Nguyenggml : remove ggml-ext.h (#21869)
2026-04-14 Georgi Gerganovmetal : fix FA support logic (#21898)
2026-04-14 Xuan-Son Nguyenmtmd: add mtmd_image_tokens_get_decoder_pos() API ...
2026-04-14 Jeff Bolzvulkan: Programmatically add RoundingModeRTE to all...
2026-04-14 Georgi Gerganovci : re-enable mac workflows (#21894)
2026-04-14 Seyoung Jeongmetal : add XIELU unary op (#20802)
2026-04-14 Adrien Gallouëtvendor : update BoringSSL to 0.20260413.0 (#21881)
2026-04-14 Richard Davisonggml : fix ARM NEON nvfp4 dot product on non-dotprod...
2026-04-14 texasichcmake: fix CMP0194 warning on Windows with MSVC (#21630)
2026-04-14 Reese Levineggml-webgpu: Update register tiling matmul to use f32...
2026-04-14 Berk Idemcommon: skip reasoning budget sampler when no budget...
2026-04-14 Jeff Bolzvulkan: Support GGML_TYPE_NVFP4 (#21455)
2026-04-14 Xuan-Son Nguyenserver: support OAI /v1/audio/transcriptions API (...
2026-04-13 Aldehir Rojascommon/gemma4 : handle parsing edge cases (#21760)
2026-04-13 Xuan-Son Nguyendocs: listing qwen3-asr and qwen3-omni as supported...
2026-04-13 Piotr Wilkin... chat: dedicated DeepSeek v3.2 parser + "official" templ...
2026-04-13 Christian Kastnerci: Also exempt 'security' tag from auto-close (#21844)
2026-04-13 Ruben Ortlamvulkan: Flash Attention DP4A shader for quantized KV...
2026-04-13 Adrien Gallouëtcommon : add download cancellation and temp file cleanu...
2026-04-13 Gaspard Petitserver: Expose build_info in router mode (#21835)
2026-04-13 Oliver SimonsCUDA: Limit DeviceSegmentedSort to immediate mode ...
2026-04-13 Xuan-Son Nguyenmtmd: use causal attn for gemma 4 audio (#21824)
2026-04-13 Rohan Jainwebui: add setting for first-line chat titles (#21797)
2026-04-13 Aleksander... webui: MCP Diagnostics improvements (#21803)
2026-04-13 Masashi YoshimuraRemove extra conditional check on debug mode. (#21798)
2026-04-13 Akarshan Biswassycl: disable Q1_0 in backend and cleanup unused variab...
2026-04-12 Sergiumtmd: fix crash when sending image under 2x2 pixels...
2026-04-12 Xuan-Son Nguyenmtmd: qwen3 audio support (qwen3-omni and qwen3-asr...
2026-04-12 Sigbjørn Skjæretconvert : force f16 or f32 on step3-vl conv weights...
2026-04-12 Xuan-Son Nguyenmtmd: add gemma 4 test (vision + audio) [no ci] (#21806)
2026-04-12 Stephen Coxmtmd: add Gemma 4 audio conformer encoder support ...
2026-04-12 Aleksander... fix: Proper messages rendering for "Show raw output...
2026-04-12 Xuan-Son Nguyendocs: add guide on how to add multimodal support (...
2026-04-11 Johannes GäßlerCUDA: skip compilation of superfluous FA kernels (...
2026-04-11 Sirui Hemtmd : add MERaLiON-2 multimodal audio support (#21756)
2026-04-11 shaofeiqiopencl: add basic support for q5_k (#21593)
2026-04-11 Johannes GäßlerTP: fix Qwen 3 Next data split (#21732)
2026-04-11 Sigbjørn Skjæretggml : fix a few instances of missing GGML_TYPE_Q1_0...
2026-04-11 Bartowskipy : Bump typer to latest to fix huggingface_hub issue...
2026-04-11 Aman GuptaCUDA: also store node->src ne/nb for graph equality...
2026-04-10 Galunidfix: Fix broken structured output when using $refs...
2026-04-10 Todor Boinovskihexagon: add support for linux on snapdragon (#21707)
2026-04-10 Max Krasnyanskyhexagon: improved Op queuing, buffer and cache manageme...
2026-04-10 Aldehir Rojascommon : better align to the updated official gemma4...
2026-04-10 Adrien Gallouëtcommon : add callback interface for download progress...
2026-04-10 MoonRide303model : make Gemma 4 shared-KV tail attn_k tensors...
2026-04-10 Rithik Sharmaggml-webgpu: support non-square subgroup matrix configs...
2026-04-10 Chen Yuanggml-webgpu: address quantization precision and backend...
2026-04-10 Adrien Gallouëtserver : ignore --alias when using --models-preset...
2026-04-10 Adrien Gallouëtcommon : fix when loading a cached HF models with unava...
2026-04-10 Johannes Gäßlercommon: mark --split-mode tensor as experimental (...
2026-04-10 Aleksander... webui: Static build output improvements (#21667)
2026-04-10 Berk Idemcommon : enable reasoning budget sampler for gemma4...
2026-04-10 Belem Zhangdocs : fix broken link to ggml-openvino in OPENVINO...
2026-04-10 Jeff Bolzvulkan: Support Q1_0 (#21539)
2026-04-10 Adrien Gallouëtcommon : add fluidity to the progress bar (#21671)
2026-04-10 Aman GuptaCUDA: fuse muls (#21665)
2026-04-09 andyluo7HIP: add CDNA4 (gfx950) architecture support for MI350X...
2026-04-09 Johannes Gäßlerggml: backend-agnostic tensor parallelism (experimental...
2026-04-09 fairydreamingggml : check return value of CUB calls used in argsort...
2026-04-09 Daniel Beveniusrequirements : update transformers to 5.5.1 (#21617)
2026-04-09 JvMwebui: add "Send message on Enter" setting (#21577)
2026-04-09 Aldehir Rojascommon : fix ambiguous grammar rule in gemma4 (#21661)
2026-04-09 Aldehir Rojascommon : simplify autoparser tagged parser rules (...
2026-04-09 Xuan-Son Nguyenmodel: fix multimodal padding token for gemma3n/gemma4...
2026-04-09 Xuan-Son Nguyenmtmd: support dots.ocr (#17575)
2026-04-09 Piotr Wilkin... vocab: add gemma4 tokenizer tests, fix edge case (...
2026-04-09 Kwa Jie Haojinja : support ensure_ascii=true, string repetition...
2026-04-09 Georgi Gerganovmetal : add missing mm-id specializations for q1_0...
2026-04-09 Aleksander... fix: Model Selector choice sync (#21628)
2026-04-09 AUTOMATIC1111server : fix grammar commandline args (#21543)
2026-04-09 Aleksander... webui: Add option to pre-encode conversation for faster...
2026-04-09 Akarshan Biswassycl : add flash-attn support for head size 512 (#21654)
2026-04-09 Marxist-Leninistci: drop v5 `all:` composition from labeler.yml (#21627)
2026-04-09 Ruben Ortlamvulkan: unify type macros to use Vx instead of _VECx...
2026-04-09 Adrien Gallouëtcommon : skip non-primary GGUF split files when selecti...
2026-04-08 Aman GuptaCUDA: also store `node->src->data` ptrs for equality...
2026-04-08 RealOrkofix: free ctx_copy in ggml_opt_free to plug per-trainin...
2026-04-08 Yuri Khrustalevserver: respect the ignore eos flag (#21203)
2026-04-08 Aldehir Rojasvocab : remove </s> eog token if gemma4 (#21492)
2026-04-08 Georgi Gerganovwebui : send both backend_sampling == false/true (...
2026-04-08 John EismeierPropose fix a couple of typos (#21581)
2026-04-08 Erik Scholzkv-cache : extend cache quantization checks (#21586)
2026-04-08 Reese Levinewebgpu : Query for adapter support when registering...
2026-04-08 Pasha Khosravimetal: Q1_0 backend (#21528)
2026-04-08 Georgi Gerganovgemma : perform per-layer projections in the first...
2026-04-08 Daniel Beveniusexamples : disable cb_eval callback for --save-logits...
2026-04-08 Piotr Wilkin... parser: fix MiniMax handling (#21573)
2026-04-08 Georgi Gerganovtests : remove obsolete .mjs script (#21615)
2026-04-08 Aleksander... chore: Update labeler to have separate labels for ...
2026-04-08 Aleksander... chore: Remove legacy files (#21606)
2026-04-08 forforever73model : support step3-vl-10b (#21287)
2026-04-08 Hamish M. Blairwebui: fix syntax highlighting lost after streaming...
2026-04-08 Martin Klacerdevops: kleidiai: provide KleidiAI-Enabled ARM Release...
2026-04-08 Aman GuptaCUDA: make cuda graphs props check faster (#21472)
2026-04-07 iacopPBKggml-cuda: ds_read_b128 for q4_0 and q4_1 mmq kernels...
2026-04-07 Daniel Beveniusgguf-py : fix missing comma after bad merge in tensor...
2026-04-07 Georgi Gerganovkv-cache : support attention rotation for heterogeneous...
2026-04-07 Reese Levineggml-webgpu: parameterize submission size and add iOS...
next