]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-07-04 Pascalui: add sync blocks so display/behavior settings can...
2026-07-04 fairydreamingggml : fix broken CPU concat implementation for quantiz...
2026-07-03 Piotr Wilkin... chat: trim messages sent to StepFun parser (fixes long...
2026-07-03 Nick Towleui: Improve performance when streaming (#25225)
2026-07-03 Pascalui: strip path and weight extension from model id in...
2026-07-03 Ruixiang Wangspec: support spec-draft-p-min in DFlash (#25246)
2026-07-03 Piotr Wilkin... cuda: enable topk-moe fusion for 288 experts (#25267)
2026-07-03 Pascalui: align persisted config with strict server schema...
2026-07-03 Pascalserver + ui: ping silent SSE streams every 1s and kick...
2026-07-03 Aleksander... ui: Add MCP Servers Opt-In for first time visitors...
2026-07-03 Gaurav GargRemove redundant CUDA copies after gated_delta_net...
2026-07-03 Alessandro... vendor : update cpp-httplib to 0.49.0 (#25218)
2026-07-02 Adrien Gallouëtllama : add llama_model_ftype_name() (#25134)
2026-07-01 lhezopencl: allow loading precompiled binary kernels from...
2026-07-01 Adrien Gallouëtcommon : use hf primary split as model path (#25194)
2026-07-01 Max Krasnyanskyhexagon: flash attention rework (optimizations, accurac...
2026-07-01 Johannes GäßlerCUDA: consistent use of __restrict__ + PDL for FA ...
2026-07-01 ragz4125ggml-cpu: add AVX2 optimization for nvfp4 dot product...
2026-07-01 Aleksander... ui Prevent tool messages from incorrectly appending...
2026-07-01 Aleksander... ui: Remove PWA navigate fallback to prevent caching...
2026-07-01 lhezopencl: initial q1_0 support (#25160)
2026-06-30 fairydreamingcuda : prevent integer truncation and overflow errors...
2026-06-30 Jürgen Schmiedmodel : register t_layer_inp for qwen3next (#25141)
2026-06-30 Pascalcommon,server: handle bracketed IPv6 literals in URL...
2026-06-30 Matt JalloCUDA: fix get_rows_back for tables with more than 65535...
2026-06-30 Johannes GäßlerCUDA: fix Gemma E4B MTP FlashAttention (#25148)
2026-06-30 Kevin Liuvulkan: roll bk loop in matmul for asahi linux (#24663)
2026-06-30 zdufordHIP: use hipBLAS for dense prefill on gfx900, keep...
2026-06-30 Masashi Yoshimuraggml-webgpu: add support for NVFP4 (#25143)
2026-06-30 Oliver SimonsRevert "sched : reintroduce less synchronizations durin...
2026-06-29 Adrien Gallouëtcommon : dedup preset and cached model entries in ...
2026-06-29 Ruben Ortlamvulkan: use flops instead of weight tensor size for...
2026-06-29 Aman GuptaDeepSeek V4 (#24162)
2026-06-29 seryogakovalyovtools/ui: restore Tailwind scanning in ignored worktree...
2026-06-29 o7sicommon : remove unused regex-partial (#25118)
2026-06-28 Xuan-Son Nguyenjinja, chat: add --reasoning-preserve flag (#25105)
2026-06-28 Aleksander... Revert "ui: fix accessibility for hover-gated interacti...
2026-06-28 Pascalui: fix stop and reasoning skip in single-model mode...
2026-06-28 Ruixiang Wangdflash: refactor draft model conversion (#25110)
2026-06-28 Aldehir Rojaschat : implement minicpm5 parser (#24889)
2026-06-28 Xuan-Son Nguyenjinja: add --dump-prog for debugging (#25086)
2026-06-28 Ruixiang Wangspec : add DFlash support (#22105)
2026-06-28 Adrien Gallouëtcommon : allow --offline in llama download (#25091)
2026-06-28 Georgi Gerganovlogs : reduce v2 (#25078)
2026-06-27 Hongqiang Wangopencl: flash attention improvement (#25069)
2026-06-27 Gaurav Garg[CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda...
2026-06-27 Neo Zhangsycl : fix failed ut cases of norm (#25044)
2026-06-27 Ruben Ortlamvulkan: fix step operator for 0 input (#25036)
2026-06-27 Christian Kastnerbinaries : Improve rpc-server and export-graph-ops...
2026-06-27 Sigbjørn Skjæretci : add windows-openvino to check-release (#25022)
2026-06-27 Sigbjørn Skjærettests : fix test-chat-template --no-common option ...
2026-06-26 Adrien Gallouëtapp : allow --version, --licenses & --help (#25054)
2026-06-26 Andreas Kieslingersched : reintroduce less synchronizations during split...
2026-06-26 Adrien Gallouëtdevops : add llama in all docker images (#25035)
2026-06-26 Xuan-Son Nguyenarg: fix handling --spec-draft-hf and --hf-repo-v ...
2026-06-26 Ravi Panchumarthyopenvino: Update to OV 2026.2.1, self-contained release...
2026-06-26 Georgi Gerganovsync : ggml
2026-06-26 Georgi Gerganovggml : bump version to 0.15.3 (ggml/1550)
2026-06-26 nullnamevulkan: opt mul_mat_vecq for mi50 (#22933)
2026-06-26 Jiang, Fishvulkan: add INTEL_XE1 arch enum and enable coopmat1...
2026-06-26 Sanjay Ahariui: fix accessibility for hover-gated interactive eleme...
2026-06-26 Jeff Bolzvulkan: Workaround compiler bug in conv2d coopmat2...
2026-06-26 leonardHONGCUDA: add cublasSgemmBatched mapping for HIP/MUSA vendo...
2026-06-26 Tarek Dakhranggml-cpu: fix SVE leftover path in ggml_vec_dot_f32...
2026-06-26 Pascalserver + ui: SSE Replay Buffer (#23226)
2026-06-26 Jassieluosycl : clamp softmax input to avoid underflow (#24941)
2026-06-26 Xuan-Son Nguyenmtmd: add more validations (#25013)
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)
next