]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
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...
2026-04-07 Aman GuptaCUDA: check for buffer overlap before fusing (#21566)
2026-04-07 Aaron Teollama-server: fix model params not propagated (#21509)
2026-04-07 Son H. Nguyenunicode : add custom Qwen2 regex handler to fix segfaul...
2026-04-07 Johannes Gäßlerllama: remove per-arch tensor name lists (#21531)
2026-04-07 Georgi Gerganovserver : fix restore for checkpoints with pos_min ...
2026-04-07 Georgi Gerganovggml : deprecate GGML_OP_ADD1 (#21363)
2026-04-07 Tom Overlundggml: Vulkan build, Linux -- output error string for...
2026-04-07 mkokervulkan: add FA dequant for q4_1, q5_0, q5_1, iq4_nl...
2026-04-07 Aldehir Rojaswebui : store reasoning_content so it is sent back...
2026-04-07 Antoine Viallonggml-cuda : fix CDNA2 compute capability constant for...
2026-04-07 Aleksander... fix: Detect streaming state in reasoning content blocks...
2026-04-07 Kabir08Fix rtl text rendering (#21382)
2026-04-07 PMZFX[SYCL] Add Q8_0 reorder optimization (~3x tg speedup...
2026-04-07 Dmytro Romanovdocs: fix typo in build.md (emdawbwebgpu -> emdawnwebgp...
2026-04-06 Masashi Yoshimuraggml-webgpu: Add the support of `MUL_MAT_ID` (#21147)
2026-04-06 Pasha Khosraviggml: add Q1_0 1-bit quantization support (CPU) (#21273)
2026-04-06 Bipin Yadavcli: fix stripping of \n in multiline input (#21485) upstream/0.0.8681
2026-04-06 Gaurav Garg[CUDA ] Write an optimized flash_attn_stream_k_fixup...
2026-04-06 Aman Guptallama-bench: add `-fitc` and `-fitt` to arguments ...
2026-04-06 Aldehir Rojasvocab : add byte token handling to BPE detokenizer...
2026-04-06 Sigbjørn Skjæretconvert : fix block_ff_dim retrieval for lfm2 (#21508)
2026-04-06 lainon1server : handle unsuccessful sink.write in chunked...
2026-04-06 Xuan-Son Nguyendocs: add hunyuan-ocr gguf, also add test [no ci] ...
2026-04-06 Georgi Gerganovconvert : set "add bos" == True for Gemma 4 (#21500)
2026-04-06 Neo Zhangsycl : handle other FA case (#21377)
2026-04-06 Yarden Talhexagon: slight optimization for argosrt output init...
2026-04-05 anchortensellama : correct platform-independent loading of BOOL...
2026-04-05 Richard Davisonmodel : add HunyuanOCR support (#21395)
2026-04-05 Ludovic Henryci : use default RISE RISC-V Runners (#21263)
2026-04-05 ddh0server : fix logging of build + system info (#21460)
2026-04-05 M1DNYT3ci: lower cuda12 floor to 12.8.1 for broader host compa...
2026-04-05 Nicholas Sparksci: fix vulkan workflow referencing non-existent action...
2026-04-04 Aldehir Rojascommon : add gemma 4 specialized parser (#21418)
2026-04-04 Dan Hoffmanserver: Fix undefined timing measurement errors in...
2026-04-04 Adrien Gallouëtcommon : respect specified tag, only fallback when...
2026-04-04 SamareshSinghllama-model: read final_logit_softcapping for Gemma...
2026-04-04 Aman Guptallama: add custom newline split for Gemma 4 (#21406)
2026-04-03 Reese Levineggml-webgpu: move from parameter buffer pool to single...
2026-04-03 Masato Nakasakaci: Add Windows Vulkan backend testing on Intel (#21292)
next