]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-07-29 Georgi Gerganovserver : add trace logging for slot similarity checking...
2026-07-29 Kaben Nanlohyconversion: fix Qwen2.5-Omni mmproj conversion regressi...
2026-07-29 Aman GuptaRPC: add tensor_memset (#25912)
2026-07-29 Geramy Lovelessadd rdna3.5, and 3 to mmq configs so they can be tuned...
2026-07-29 Satinder Grewalmodel: add NextN/MTP speculative decoding support for...
2026-07-28 Guido Imperialemodel: Add Laguna-S-2.1 LLM_TYPE (#26233)
2026-07-28 Reese Levineggml-webgpu: Fix some binding alias issues to support...
2026-07-28 Hongqiang Wangopencl: skip the Adreno KQ/KQV image kernels for multi...
2026-07-28 Daniel Beveniusmtmd : add Nemotron 3 Nano Omni support (parakeet)...
2026-07-28 Aleksander... ui: rendering performance follow-up (#26097)
2026-07-28 Julien Jerphaniondocs: Adapt conda-forge package name (#26229)
2026-07-28 Xuan-Son Nguyenserver: abstract llama_memory calls to common_memory...
2026-07-28 Aman Guptaggml : set output of view src (#25729)
2026-07-28 Jeff Bolzvulkan: add iq4_nl support back to FA (#24585)
2026-07-28 Bhavik Shardaggml-cuda: add chunked SSD matmul for Mamba-2 prefill...
2026-07-28 王金旭spec: add DSpark speculative decoding (#25173)
2026-07-28 Aldehir Rojascommon/chat: add specialized minimax m3 parser (#26210)
2026-07-28 meatposessycl: fix use-after-return of the SDPA scale in the...
2026-07-28 Georgi Gerganovserver : add extra trace log for prompt similarity...
2026-07-28 Nick Lafleurggml-metal: FWHT kernel for metal backend (#25924)
2026-07-28 Ruixiang Wangspec: add eagle3-v3 support for gpt-oss model (#25794)
2026-07-28 Georgi Gerganovcontrib : add guideline about the "merge ready" label...
2026-07-27 BeinseziiDisable -ffast-math on HIP (#25495)
2026-07-27 Xuan-Son Nguyenmtmd: support MiMo-V2.5 audio input (RVQ-based model...
2026-07-27 Adrien Gallouëtcommon : add common_print_available_devices() (#26170)
2026-07-27 zqlmodel: Add support for Nanbeige4.2 (#25994)
2026-07-27 Jonas Jankaitisfit : count nextn (MTP) blocks in n_gpu_layers so front...
2026-07-27 Titaniumtownsycl(build): parallelize ocloc invocations (#25903)
2026-07-27 Georgi Gerganovggml : adjust logic for offloading ops to weight's...
2026-07-27 Georgi Gerganovtests : remove unnecessary sync in test-save-load-state...
2026-07-27 Pascalcommon: fix explicit -md precedence over draft sidecar...
2026-07-27 Xuan-Son Nguyendocs: add exception about weight folding (#26168)
2026-07-27 shalinib-ibmggml-cpu: Enable BF16 tiled gemm optimization on PowerP...
2026-07-27 Aaron Teoargs: add `-lm mlock` where it mlocks but doesnt mmap...
2026-07-27 Pascalserver + ui: fix stream routes for model names containi...
2026-07-27 rankaiyxui: Fix symbolic math tool JS sandbox prompt (#26131)
2026-07-26 timkhronosmtmd: Add Vision Support for Minimax-M3 (#25113)
2026-07-26 Xuan-Son Nguyenmtmd: fix android build (#26150)
2026-07-26 Piero Evangelistaui: fix system message edit box not expanding to fit...
2026-07-26 BartowskiKeep Minimax's indexer tensors at F32 for speed and...
2026-07-26 Pascalui: detect the conversation import format from file...
2026-07-26 Xuan-Son Nguyencommon: add `subproc.h` wrapper, disabled on android...
2026-07-26 Eric Hartfordmtmd: add GLM-5.2-Vision (#26126)
2026-07-26 timkhronosmodel: Add MiniMax-M3 (MSA: MiniMax Sparse Attention...
2026-07-26 yzyyzyhhhopencl: fix fused RMS norm mul view offset (#26085)
2026-07-26 Pascalui: fix context gauge card regressions and land at...
2026-07-26 Reese Levineggml-webgpu: Fix WASM compilation with OpenMP (#25943)
2026-07-25 Nicky Mouhacommon : use-after-free when loading LoRA adapter fails...
2026-07-25 Xuan-Son Nguyenserver: support MCP stdio (#26062)
2026-07-25 Todor Boinovskihexagon: partial im2col support (#26007)
2026-07-25 hogeheer499... common : skip empty implicit default preset (#25643)
2026-07-25 Xuan-Son Nguyenserver: add format arg to datetime tool (#26117)
2026-07-25 Tekin Ertekinserver : add missing task parameters(adaptive_target...
2026-07-25 Adrien Gallouëtvendor : update cpp-httplib to 0.51.0 (#26067)
2026-07-25 Yongmin Yoo 유용민Update ggml/src/gguf.cpp : Defined virtual keyword...
2026-07-25 Aldehir Rojascommon : add support for multiple end sequences in...
2026-07-25 helanfxztests: synchronize save-load-state generation (#26056)
2026-07-24 Zach Winterui: reduce per-token render cost when streaming (...
2026-07-24 Pascalui: remove render effects (#26083)
2026-07-24 Pedro Cuencamodel: add GLM 5.2 Indexer support (#25407)
2026-07-24 Pascalui: fix MCP server display name conflicts in tools...
2026-07-24 Nigel Boschserver: support "reasoning_effort": "none" in OAI API...
2026-07-24 Xuan-Son Nguyenllama: various bug fixes (#26051)
2026-07-24 Johannes GäßlerHIP: remove rocWMMA FlashAttention (#26046)
2026-07-24 Hongqiang Wangopencl: cache compiled cl_program binaries on disk...
2026-07-24 kumaalopencl: do not treat NULL-mask flash attention as causa...
2026-07-24 Xuan-Son Nguyenskill: create `add-new-model` and `code-review` (#26042)
2026-07-24 PascalUI: Fix settings precedence, Factory < Admin (--ui...
2026-07-24 Matt Thompsoncohere2 moe template parser: enforce JSON schema for...
2026-07-24 Xuan-Son Nguyenvendor: update subprocess.h (#26061)
2026-07-24 Max Krasnyanskyhexagon: further improved pipeline of the core bits...
2026-07-23 adgup-qtihexagon: fix Windows crash when op_poll is enabled...
2026-07-23 Johannes GäßlerCUDA: fix external compilation of q1_0 MMQ (#25778)
2026-07-23 Aaron Teoargs: refactor mlock/mmap/directio into load-mode ...
2026-07-23 Pascalcontrib: fix leftovers from the AI usage policy update...
2026-07-23 Ilia Ilmermetal : add f16 type support to leaky relu (#25981)
2026-07-23 Shahir BIn... conversion: fix non-MoE NomicBert GGUF conversion error...
2026-07-22 Xuan-Son Nguyencontrib: allow all AI-generated code in general (#26012)
2026-07-22 Pascalui: Add a "Default" option for the reasoning selector...
2026-07-22 Oliver SimonsCUDA: Improve NVFP4 W4A4 activation quantization (...
2026-07-22 Todor Boinovskihexagon: activation ops update (#25974)
2026-07-22 Niklas Wenzelmtmd: use RAII for setting and resetting non-causal...
2026-07-22 rankaiyxfeat(ui): add symbolic math support to JS sandbox via...
2026-07-22 Piotr Wilkin... minor: fix reasoning preserve var for DS4 [no ci] ...
2026-07-22 Pascalcommon: infer the speculative type from the draft repo...
2026-07-22 Piotr Wilkin... Fix DeepSeek4 crafted template (#25414)
2026-07-22 shalinib-ibmggml: enable PowerPC backend variants on AIX (#25983)
2026-07-22 KyleHagyci : fix SYCL package shared library lookup (#25987)
2026-07-22 m1elwebgpu : add CONV_2D_DW (depthwise conv2d) kernel ...
2026-07-22 Pascalcuda: GET_ROWS quants (#25962)
2026-07-22 helanfxzllama-arch: fix DeepSeek4 APE tensor op (#25945)
2026-07-22 Joe RowellAdd support for Laguna XS.2 & M.1 (#25165)
2026-07-21 wendadawenconvert: fix handle HunyuanVL XD-RoPE config (#25514)
2026-07-21 Gerben van Vmtmd : use align_corners for qwen3vl vision position...
2026-07-21 Wei Wanghexagon: check tensor type when reusing descriptors...
2026-07-21 Aman Guptacuda: add sqrt_softplus in topk-moe for dsv4 (#25896)
2026-07-21 Kamalesh VSkleidiai : warn once when a weight type has no KleidiAI...
2026-07-21 Pascalcommon: resolve draft repo to its requested sidecar...
2026-07-21 Pascalserver: return 400 instead of 500 on validation error...
2026-07-21 fairydreamingserver : properly handle null llama_context (#25868)
next