]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-06-26 leonardHONGCUDA: batch out_prod broadcast (dps2>1) path with cubla...
2026-06-26 Arsen Arutunanmamba2: remove hardcoded 2x expansion factor and invali...
2026-06-26 shaofeiqiopencl: flush profiling batch at shutdown for incomplet...
2026-06-25 Sigbjørn Skjæretxcframework : disable mtmd video on i/tv/visionos ...
2026-06-25 Tarek Dakhranmodel : Add label for LFM2.5-230M (#25008)
2026-06-25 Oliver SimonsCUDA: Various fixes to `cpy.cu` (#25000)
2026-06-25 Xuan-Son Nguyenmisc: fix labeler (#25012)
2026-06-25 Xuan-Son Nguyenserver: use status code 403 for disabled features ...
2026-06-25 Xuan-Son Nguyenmisc: update lables (#24920)
2026-06-25 Xuan-Son Nguyencommon: refactor model handling (#24980)
2026-06-25 Kashif Rasuldocs : Eagle3 qwen3 draft model support (#24977)
2026-06-25 Adrien Gallouëtapp : add the llama download subcommand (#24982)
2026-06-25 fairydreamingggml : address integer overflows in binary ops CUDA...
2026-06-25 Pascalui: fix always-show-sidebar-on-desktop setting after...
2026-06-25 Christopher... tests : synchronize contexts at end of test-thread...
2026-06-25 Abraham Gonzalezbuild: include libmtmd in Apple XCFramework (#21935)
2026-06-25 Sigbjørn Skjæretquant : fix quantizing moe with mtp (#24986)
2026-06-25 David Spruillsycl : support --split-mode tensor (#24152)
2026-06-25 Neo Zhangsycl : fix the failed UT cases of conv_3d (#24900)
2026-06-25 lhezopencl: support non-contig rows in norm (#24965)
2026-06-25 Piotr Wilkin... chat: harden caps check (#24973)
2026-06-24 Max Krasnyanskyhexagon: MUL_MAT and MUL_MAT_ID rework : 32x32 tiled...
2026-06-24 Saba Fallahmtmd: model: unlimited-ocr: converter + parity test...
2026-06-24 Xuan-Son Nguyencommon: remove unused json-partial (#24968)
2026-06-24 Wagner Brunavulkan: allow reducing the graph submission batches...
2026-06-24 liminfei-amdvulkan: fail the build when a shader fails to compile...
2026-06-24 Pascalui: loading bar below the model picker (#24931)
2026-06-24 Aleksander... ui: New Logo + Navigation cleanup & Mobile UI/UX improv...
2026-06-24 Tarek Dakhranmodel : Add LFM2.5-ColBERT-350M and LFM2.5-Embedding...
2026-06-24 Jeff Bolzvulkan: Apply bias before softmax in FA, to avoid overf...
2026-06-23 kononnableserver : check draft context creation error (#24922)
2026-06-23 Jeff Bolzvulkan: support all backend tests for SQR/SQRT/SIN...
2026-06-23 Jeff Bolzvulkan: Support GET_ROWS_BACK (#24883)
2026-06-23 Jeff Bolzvulkan: support CONV_3D (#24612)
2026-06-23 Jeff Bolzvulkan: make mul_mm ALIGNED a spec constant (#24689)
2026-06-23 Xuan-Son Nguyenserver: fix remote preset handling, add test (#24938)
2026-06-23 Wyatt Caldwellvulkan: link ggml-cpu when GGML_VULKAN_CHECK_RESULTS...
2026-06-23 Gabe Goodhartmodel: Granite Speech Plus (#24818)
2026-06-23 Masashi Yoshimuraggml-webgpu: improve MTP inference by using mat-vec...
2026-06-23 Masashi Yoshimuracodeowners: add yomaytk to ggml-webgpu (#24930)
2026-06-23 Aldehir Rojasserver: improve user message detection and create check...
2026-06-23 Shawn Guopencl: q8_0 gemv precision improvement (#24923)
2026-06-22 Matt Thompsonserver : Add id to tool call responses api (#24882)
2026-06-22 Mahdiou Dialloui: Prioritize favorite models in model selection ...
2026-06-22 Xuan-Son Nguyenserver: (router) move model downloading to dedicated...
2026-06-22 Xuan-Son Nguyenserver: refactor/generalize input file schema (#24299)
2026-06-22 Pascalui: model status and load progress via /models/sse...
2026-06-22 Neo Zhang[SYCL] support bf16 on bin_bcast OP and unary OPs ...
2026-06-22 Tim Neumannsampling : remove unconditional softmax+sort in top...
2026-06-22 Pascalserver: fix edit_file crash on append at end of file...
2026-06-22 aafsmarakdocs/android.md: Add dependency `libandroid-spawn`...
2026-06-21 Aldehir Rojascommon/peg : implement ac parser for stricter grammar...
2026-06-21 Xuan-Son Nguyenserver: fix report progress for loading spec models...
2026-06-21 Xuan-Son Nguyenserver: refactor batch construction (#24843)
2026-06-21 Xuan-Son Nguyenmtmd: fix mtmd_get_memory_usage (#24867)
2026-06-21 Sigbjørn Skjæretjinja : implement call statement (#24847)
2026-06-21 Xuan-Son Nguyenmtmd: add load progress callback (#24865)
2026-06-21 Xuan-Son Nguyenserver: add "verbose" field to schema (#24864)
2026-06-21 Xuan-Son Nguyenserver: real-time model load progress tracking via...
2026-06-21 Georgi Gerganovminor : clean-up whitespaces (#24862)
2026-06-21 YiChen Lvspec : Support Step3.5/3.7 flash mtp3 (#24340)
2026-06-21 Aldehir Rojascommon/peg : refactor until gbnf grammar generation...
2026-06-20 Aldehir Rojascommon/json-schema-to-grammar : align spacing rules...
2026-06-20 Guanhuai Zhangfix(hexagon): use padded stride for ssm-conv weights...
2026-06-20 Adrien Gallouëtllama : use LLM_KV for quantization_version & file_type...
2026-06-20 Xuan-Son Nguyenarg: try fixing test-args-parser randomly fails (#24826)
2026-06-20 Muhammad Salemrelease: add missing link for win opencl adreno arm64...
2026-06-20 Matti4server: avoid forwarding auth headers in CORS proxy...
2026-06-20 Aldehir Rojasdocker : prebuild web UI for s390x build [no release...
2026-06-20 davidrhodusmodel : glm-dsa load DSA indexer tensors as optional...
2026-06-20 Adrien Gallouëtggml : optimize AMX (#24806)
2026-06-20 Sigbjørn Skjæretconvert : more consistent handling of rope_parameters...
2026-06-19 Masashi Yoshimuraggml-webgpu: add adapter toggles for F16 on Vulkan...
2026-06-19 Xuan-Son Nguyenserver: refactor child --> router communication (#24821)
2026-06-19 Adrien Gallouëtserver : optimize get_token_probabilities (#24796)
2026-06-19 Xuan-Son Nguyenmtmd, arg: fix utf8 handling on windows (#24779)
2026-06-19 Xuan-Son Nguyenserver: remove all internal mentions about "webui"...
2026-06-19 Mikolaj Kucharskiarg: Add comment line support to --api-key-file (#23168)
2026-06-19 Alessandro... vendor : update cpp-httplib to 0.48.0 (#24787)
2026-06-19 Xuan-Son Nguyenserver: add --agent arg, remove redundant webui naming...
2026-06-19 Aldehir Rojasdocker : build the UI (#24794)
2026-06-19 Xuan-Son Nguyenmtmd: several bug fixes (#24784)
2026-06-19 Ruixiang Wangspec: support eagle3 for qwen3.5 & 3.6 (#24593)
2026-06-19 Xuan-Son Nguyenserver: fix non-bound n_discard value (ctx shifting...
2026-06-19 Georgi Gerganovsync : ggml
2026-06-19 Georgi Gerganovggml : bump version to 0.15.2 (ggml/1548)
2026-06-19 Georgi Gerganovpi : remove docs from system prompt (#24791)
2026-06-19 Georgi Gerganovserver : consolidate slot selection into get_available_...
2026-06-19 shalinib-ibmggml-cpu: support K tails in power10 Q8/Q4 MMA matmul...
2026-06-18 Xuan-Son Nguyenmtmd: add batching support for internvl (#24775)
2026-06-18 PascalGgml/cuda col2im 1d (#24417)
2026-06-18 Regunaserver: add "X-Accel-Buffering": "no" header to streami...
2026-06-18 Xuan-Son Nguyenmtmd: add batching for mtmd-cli, add video tests (...
2026-06-18 o7sicmake : fix ui build with read-only source (#24752)
2026-06-18 Xuan-Son Nguyenmtmd: refactor llava-uhd overview image handling (alway...
2026-06-18 Max Krasnyanskyhexagon: support for op-trace (fine-grain tracing...
2026-06-18 Kangjia Gaodocs: fix export-lora --lora-scaled syntax [no release...
2026-06-18 Xuan-Son Nguyenserver: (router) fix stopping_thread potentially hang...
2026-06-18 Xuan-Son Nguyenserver: add "schema" and validation (#24150)
2026-06-18 Aarni Koskelaserver : add last-5-seconds generation speed display...
next