]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-06-09 Reese Levineggml-webgpu: Add clang-format job (#24308)
2026-06-08 Masashi Yoshimuraggml-webgpu: Improve prefill speeds for k-quants +...
2026-06-08 Max Krasnyanskymtp: support for gemma-4 E2B and E4B assistants (#24282)
2026-06-08 Aldehir Rojasserver : do not parse when flushing http headers (...
2026-06-08 Pascalgraph: guard iswa kq_mask on its own buffer (#24294)
2026-06-08 Nikhil Jain[ggml-webgpu] Handle buffer overlap / buffer aliasing...
2026-06-08 Nikhil Jain[ggml-webgpu] Implement 2D workgroups for scale, binary...
2026-06-08 Xuan-Son Nguyendocker: install ffmpeg in the released image (#24302)
2026-06-08 Xuan-Son Nguyenmtmd : add video input support (#24269)
2026-06-08 Georgi Gerganovsync : ggml
2026-06-08 Georgi Gerganovggml : bump version to 0.14.0 (ggml/1533)
2026-06-08 Xuan-Son Nguyencli: fix spinner not show during prompt processing...
2026-06-08 Jeff Bolzvulkan: Use cm2 decode_vector for mul_mat_id B matrix...
2026-06-08 Ruben Ortlamcuda: reset cuda context after reading memory size...
2026-06-08 Harkirat GillHIP: add gfx1152 and gfx1153 to RDNA3.5 (#24129)
2026-06-08 Xuan-Son Nguyenmetal : fix im2col 1D case (audio models) (#24220)
2026-06-08 Neo Zhang[SYCL] Update compute runtime version to 26.x in docker...
2026-06-07 ddh0common : relax sampler name matching (#23744)
2026-06-07 David Friehsconvert : fix conversion for Mistral-Medium-3.5-128B...
2026-06-07 Georgi Gerganovkv-cache : avoid kv cells copies (#24277)
2026-06-07 Pascalkv-cache: follow the source cache size when sharing...
2026-06-07 Aman Guptallama : add Gemma4 MTP (#23398)
2026-06-07 Sigbjørn Skjæretspec : fix vocab compatibility check (#24256)
2026-06-07 konradmbarg: Skip mmproj download when user supplied mmproj...
2026-06-07 Sigbjørn Skjæretconvert : fix Gemma4 with no audio encoder (#24242)
2026-06-07 Sigbjørn Skjæretdocker : bump cuda13 to 13.3.0 (#24228)
2026-06-06 Tarek Dakhrancommon/chat : fix LFM2/LFM2.5 reasoning round-trip...
2026-06-06 Xuan-Son Nguyenmtmd: support "frame merge" for qwen-vl-based models...
2026-06-06 Adrien Gallouëtcompletion : remove useless statics (#24226)
2026-06-06 Adrien Gallouëtcompletion : fix format specifier in LOG_INF (#24213)
2026-06-06 Xuan-Son Nguyenmtmd, server: add "placeholder bitmap" for counting...
2026-06-06 Ruben Ortlamvulkan: check coopmat2 features before reporting suppor...
2026-06-06 Sigbjørn Skjæretmodel : rename local n_layer_all variable (#24209)
2026-06-06 Sigbjørn Skjæretcontext : fix off-by-one comparisons to n_gpu_layers...
2026-06-05 lhezopencl: improve get_rows, cpy, concat and q6_k flat...
2026-06-05 Tarek Dakhrancommon/chat : unify and fix LFM2/LFM2.5 tool parser...
2026-06-05 Ruben Ortlamvulkan: add fwht support for Intel with shmem reduction...
2026-06-05 Xuan-Son Nguyenmodel: fix build failed (#24193)
2026-06-05 Gabe Goodhartmodel, mtmd: Granite4 Vision (#23545)
2026-06-05 Johannes GäßlerTP: round up granularity to 128 (#24180)
2026-06-05 therealkenccli: fix model params not propagated (#23893)
2026-06-05 Georgi Gerganovmodel : fix llama_model::n_gpu_layers() (#24188)
2026-06-05 Pascalui: run npm install when package-lock.json is newer...
2026-06-05 MarioFix link to available UI settings (#24169)
2026-06-05 Xuan-Son Nguyenui: add ignore-scripts=true to npmrc (#24149)
2026-06-05 Pedro Cuencadocs: Update quantization readme (#24133)
2026-06-05 Georgi Gerganovminor : fix lint issues (#24165)
2026-06-05 Georgi Gerganovhparams : refactor `hparams.n_layer` (#24060)
2026-06-05 Charles Xukleidiai : dynamic chunck-based scheduling for hybrid...
2026-06-05 Oliver SimonsCUDA: enroll mul_mat_vec_q_moe into pdl (#24087)
2026-06-05 Daniel Beveniusci : build-msys job slimming [no ci] (#24157)
2026-06-05 Mason Milburnsycl : port multi-column MMVQ from CUDA backend (#21845)
2026-06-04 Georgi Gerganovserver : disable on-device spec checkpoints (#24108)
2026-06-04 Xuan-Son Nguyenarg: fix double mtp downloads (#24128)
2026-06-04 viggywebui: [a11y] fix keyboard navigation issues in chat...
2026-06-04 BartowskiMove duplicated imatrix code into single common imatrix...
2026-06-04 Aleksander... ui: Fixed packages (#24119)
2026-06-04 MagicExistsui: added single line reasoning preview (#23601)
2026-06-04 forforever73return filter to save memory (#24125)
2026-06-04 Pedro Cuencaconvert: Fix Gemma 4 Unified conversion (#24118)
2026-06-04 Kartik Sirohiggml: vectorize ggml_vec_dot_q4_1_q8_1 with WASM SIMD12...
2026-06-04 Yongyue Sunserver: avoid unnecessary checkpoint restore when new...
2026-06-04 Xuan-Son Nguyenagents: refactor, include more guidelines (#24111)
2026-06-04 Pascalwebui: fix tool selector toggle/counter, key tools...
2026-06-04 Gerard Martinezbuild : use umbrella Headers directory for XCFramework...
2026-06-04 A Bserver : add header to tools/server/server-http.h ...
2026-06-04 Andrea Richiardicmake: skip cvector-generator and export-lora when...
2026-06-04 Andreifix(mtmd): handle Gemma 4 audio projector embedding...
2026-06-04 Georgi Gerganovreadme : add status badges (#24104)
2026-06-04 Georgi Gerganovtests : refactor test-save-load-state to accept token...
2026-06-04 Georgi Gerganovmetal : reduce rset heartbeat from 500ms -> 5ms (#24074)
2026-06-04 Reese Levineggml-webgpu: FlashAttention refactor + standardize...
2026-06-04 rehan-10xengineerggml-cpu: extend RVV quantization vec dot to higher...
2026-06-04 Todd Malsbarysycl : Improve SYCL doc (#23025)
2026-06-03 Andreimtmd: fix Gemma 4 unified FPE (#24088)
2026-06-03 Aman Guptaqwen35: use post-norm hidden state for MTP (#24025)
2026-06-03 Xuan-Son Nguyenmtmd: enable non-causal vision for gemma 4 unified...
2026-06-03 Xuan-Son Nguyenmtmd, model: allow skip build_vit() (#24077)
2026-06-03 Aleksander... ui: Mermaid Diagrams in chat + interactive preview...
2026-06-03 Andreas KieslingerAvoid PDL race conditions by disabling __restrict__...
2026-06-03 Charles Xuggml-cpu: use runtime SVE width in FWHT (#24059)
2026-06-03 Aman Guptacuda: reserve space for quantize kv-cache at startup...
2026-06-03 Georgi Gerganovtests : add support for qwen3 SSM archs (#24031)
2026-06-03 Alessandro... update BoringSSL to 0.20260526.0 (#23794)
2026-06-03 Georgi Gerganovci : disable ccache for msvc windows release jobs ...
2026-06-03 Ryan Mangenoarg : removed unecesary mmproj download when users...
2026-06-02 lhezopencl: use flat variants of q4_K and q6_K gemv for...
2026-06-02 Max Krasnyanskyhexagon: profiler output fix and script updates (#24042)
2026-06-02 Mikhail Podvitskiimodel: add Mellum architecture (#23966)
2026-06-02 Hans Florianmodel : support granite multilingual embeddings R2...
2026-06-02 Piotr Wilkin... StepFun 3.5 MTP (#23274)
2026-06-02 Daniel Beveniuscommon : fix state save in common_prompt_batch_decode...
2026-06-02 Xuan-Son Nguyenserver: add SSE ping interval (#24013)
2026-06-02 Georgi Gerganovci : reduce self-hosted server workflow jobs (#24012)
2026-06-02 Mikhail Podvitskiidocs : update HOWTO-add-model.md (#23883)
2026-06-02 Marcos Del... ui: simplify network error handling (#23431)
2026-06-02 Aleksander... ui: Add Thinking mode toggle with reasoning effort...
2026-06-02 Georgi Gerganovkv-cache : SWA checkpoints store only non-masked cells...
2026-06-02 forforever73convert : support Step3.7-Flash (#23845)
2026-06-02 Georgi Gerganovllama : deprecate `llama_set_warmup` (#24009)
next