]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-06-13 Georgi Gerganovfit : wrap llama_device_memory_data (#24522)
2026-06-13 Muhammad Salemfix sycl links in release notes (#24527)
2026-06-12 Xuan-Son Nguyenmtmd: add batching API (#24384)
2026-06-12 Sigbjørn Skjæretci : unbreak release harder (#24545)
2026-06-12 Sigbjørn Skjæretci : unbreak release (#24544)
2026-06-12 Georgi Gerganovserver : fix reasoning budget WebUI precedence over...
2026-06-12 Ruben Ortlamvulkan: add pipeline barriers for memcpy read operation...
2026-06-12 Aleksander... ui: PWA support (#23871)
2026-06-12 Georgi Gerganovfit : avoid including llama-ext.h in fit.h (#24506)
2026-06-12 Georgi Gerganovsync : ggml
2026-06-12 Georgi Gerganovggml : bump version to 0.15.1 (ggml/1541)
2026-06-12 Adrien Gallouëtvendor : update cpp-httplib to 0.47.0 (#24395)
2026-06-12 PascalUI/jpeg exif orientation (#24196)
2026-06-12 Ruixiang Wangspec: add EAGLE3 speculative decoding support (#18039)
2026-06-12 ZihaoMuggml: support concat for scalar types at cuda backend...
2026-06-12 Neo Zhang[SYCL] Fix CI build & release for SYCL backend (#24387)
2026-06-12 shaofeiqiopencl: add q5_0/q5_1 gemm and gemv kernels for Adreno...
2026-06-11 wencandocker : support specifying the GCC version for CUDA...
2026-06-11 Jeff Bolzvulkan: ifdef eMesaHoneykrisp (build fix) (#24479)
2026-06-11 Georgi Gerganovsync : ggml
2026-06-11 Georgi Gerganovggml : bump version to 0.15.0 (ggml/1539)
2026-06-11 Winston Mavulkan: add fast path for contiguous buffer transfers...
2026-06-11 Kevin Liuvulkan: use medium matmul tile on Asahi Linux (#24306)
2026-06-11 Xuan-Son Nguyenserver: skip unused log lines on router mode (#24463)
2026-06-11 o7sivocab : adopt leading TemplateProcessing special token...
2026-06-11 o7sivocab : refactor normalizer flags into options struct...
2026-06-11 Aldehir Rojasserver : skip checkpoints beyond pos_next (#24411)
2026-06-10 Adrien Gallouëtvendor : update LibreSSL to 4.3.2 (#24397)
2026-06-10 Gaurav GargRemove padding and multiple D2D copies for MTP (#24086)
2026-06-10 Tarek Dakhranchat: fix LFM2/LFM2.5 ignoring json_schema (#24377)
2026-06-10 Oliver SimonsCUDA: Fix ssm_scan_f32 data-races (#24360)
2026-06-10 Sigbjørn Skjæretci : bump komac version (#24396)
2026-06-10 ddh0speculative : fix "ngram-map-k4v" name in logging ...
2026-06-09 Rémy Mathieuwebui: implement pinned conversations support (#21387)
2026-06-09 Aarnav Paigraph: Fix granite speech model inference by applying...
2026-06-09 Sigbjørn Skjæretci : fix windows release (#24369)
2026-06-09 Pascalui: add opt-in run_javascript frontend tool (#24244)
2026-06-09 Saba Fallahmtmd: build_vit batching (#24352)
2026-06-09 Jeff Bolzvulkan: reduce iq1 shared memory usage for mul_mm ...
2026-06-09 Ruben Ortlamvulkan: add `v_dot2_f32_f16` support in matrix-matrix...
2026-06-09 Nick Towleui: Fix excessive style recalculation on hover (#24243)
2026-06-09 Xuan-Son Nguyenmtmd: refactor video subproc handling (#24316)
2026-06-09 jacekpoplawskiserver: log prompts to directory (#22031)
2026-06-09 Pascalui: fix mobile chat form overflow and bust stale bundle...
2026-06-09 Pascalggml : add GGML_OP_COL2IM_1D (#24206)
2026-06-09 fieshserver : do not clear slots without unified KV cache...
2026-06-09 Sigbjørn Skjæretmodels : fix plamo2 attention_key/value_length regressi...
2026-06-09 Yash Raj Pandeyggml-cpu : fix rms_norm_back wrong output under in...
2026-06-09 ravel7524Remove case for GGML_TYPE_Q4_K in mvvq.cu (#23528)
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)
next