]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-12-06 Georgi Gerganovcontrib : stale PRs (#17803)
2025-12-06 Georgi Gerganovmetal : fix build(#17799)
2025-12-06 Masato Nakasakavulkan: Replace deprecated VK_EXT_validation_features...
2025-12-06 Masato Nakasakavulkan: Fix mismatch in TOPK_MOE unit test (#17541)
2025-12-05 Jeff Bolzvulkan: add more num_blocks instantiations in rms_norm...
2025-12-05 Jeff Bolzvulkan: fix top_k bug when there are ties in the input...
2025-12-05 Aclyvulkan : support conv-2d with large output size (#17685)
2025-12-05 Reese Levineggml webgpu: unary op suppport, code refactoring, ops...
2025-12-05 Jeff Bolzvulkan: enable mmvq for q2_k on NVIDIA (#17675)
2025-12-05 Jeff Bolzvulkan: set all memory allocations to high priority...
2025-12-05 Georgi Gerganovrpc : fix alloc size logic (#17116)
2025-12-05 Georgi Gerganovmetal : add residency sets keep-alive heartbeat (#17766)
2025-12-05 Johannes GäßlerHIP : fix RDNA4 build (#17792)
2025-12-05 Pascalfix: prevent segfault in tokenizer on highly repetitive...
2025-12-05 Adrien Gallouëtci : fix winget workflow (#17790)
2025-12-05 shalinib-ibmQ4/Q8 Tiled Gemm Optimization. (#16999)
2025-12-05 Piotr Wilkin... Add pwilkin to CODEOWNERS for chat files (#17789)
2025-12-05 Johannes GäßlerCUDA: fix FA VKQ accumulator overflow (#17746)
2025-12-05 Jiacheng (Jason... HIP: enable WMMA-MMQ INT kernels for RDNA 3 (#17576)
2025-12-05 Sigbjørn Skjæretci : transform release binary root dir in tar to llama...
2025-12-04 Gabe Goodhartdocs : update ops.md (Metal, BLAS) (#17768)
2025-12-04 Piotr Wilkin... Add support for CUMSUM and TRI for CUDA. (#17584)
2025-12-04 Gabe Goodhartmetal: TRI, FILL, EXPM1, SOFTPLUS (#16623)
2025-12-04 Xuan-Son Nguyenserver: strip content-length header on proxy (#17734)
2025-12-04 Xuan-Son Nguyenserver: move msg diffs tracking to HTTP thread (#17740)
2025-12-04 Daniel Beveniusexamples : add missing code block end marker [no ci...
2025-12-04 Daniel Beveniuscommon : skip model validation when --help is requested...
2025-12-04 Alberto Cabrera... ggml-cpu : remove asserts always evaluating to false...
2025-12-04 SmartestWashingMachineconvert: use existing local chat_template if mistral...
2025-12-04 Adrien Gallouëtcmake : simplify build info detection using standard...
2025-12-04 Sigbjørn Skjæretci : disable ggml-ci-x64-amd-* (#17753)
2025-12-04 Adrien Gallouëtcommon: use native MultiByteToWideChar (#17738)
2025-12-04 Georgi Gerganovmetal : use params per pipeline instance (#17739)
2025-12-04 Georgi Gerganovllama : fix sanity checks during quantization (#17721)
2025-12-04 Adrien Gallouëtbuild : move _WIN32_WINNT definition to headers (#17736)
2025-12-04 Jeff Bolzbuild: enable parallel builds in msbuild using MTT...
2025-12-03 Herman Semenoffggml-cpu: remove duplicate conditional check 'iid'...
2025-12-03 Piotr Wilkin... Add a couple of file types to the text section (#17670)
2025-12-03 SmartestWashingMachineconvert : support latest mistral-common (fix conversion...
2025-12-03 Aleksander... Use OpenAI-compatible `/v1/models` endpoint by default...
2025-12-03 Andika Wasistowebui: Fix zero pasteLongTextToFileLen to disable conve...
2025-12-03 Johannes GäßlerCUDA: generalized (mma) FA, add Volta support (#17505)
2025-12-03 Georgi Gerganovchat : reserve memory in compute_diffs and improve...
2025-12-03 Pascalserver: add router multi-model tests (#17704) (#17722)
2025-12-03 Adrien Gallouëtserver : fix bad fmt, size() is a size_type (#17735)
2025-12-03 Adrien Gallouëtcmake: explicitly link against crypt32 on non-MSVC...
2025-12-03 Georgi Gerganovmetal : fix data race in pipeline library (#17731)
2025-12-03 jiahao suci : remove the build of openeuler-cann in release...
2025-12-03 Aldehir Rojascommon : introduce composable PEG parser combinators...
2025-12-03 Pascalserver: fix duplicate HTTP headers in multiple models...
2025-12-03 Reese Levineggml webgpu: add support for emscripten builds (#17184)
2025-12-03 Sigbjørn Skjæretci : move release details to the top visible by default...
2025-12-03 Herman Semenoffggml, llama : use defaulted constructors/destructors...
2025-12-03 Marcos Del... build: document how to compile with Vulkan using Debian...
2025-12-02 Xuan-Son Nguyenserver: add --media-path for local media files (#17697)
2025-12-02 Xuan-Son Nguyenmtmd: fix --no-warmup (#17695)
2025-12-02 Ali Tariqci : RVV1.0 builds with tests (#16682)
2025-12-02 Jeff Bolzvulkan: Reduce temporary memory usage for TOP_K (#17623)
2025-12-02 xiaobing318cmake : add utf8 compilation options for msvc (#17682)
2025-12-02 Chad VoegeleServer: Change Invalid Schema from Server Error (500...
2025-12-02 Adrien Gallouëtggml : use svcntb() for SVE vector length detection...
2025-12-02 TianHao324CANN: Disable Ger operator of OUT_PROD on 310p device...
2025-12-02 Daniel Beveniusggml : remove redundant n_copies check when setting...
2025-12-02 Eric Curtincodeowners : remove ericcurtin (#17658)
2025-12-02 Adrien Gallouëtllama : fix signed comparison warning on FreeBSD (...
2025-12-02 Xuan-Son Nguyenconvert: add error message for mistral3 quantized weigh...
2025-12-02 Xuan-Son Nguyenserver: remove default "gpt-3.5-turbo" model name ...
2025-12-02 senhtryserver: fixing naming conflict res_error in server...
2025-12-02 Xuan-Son Nguyenserver: explicitly set exec path when create new instan...
2025-12-02 Adrien Gallouëtci : skip winget update when not in ggml-org (#17465)
2025-12-02 Adrien Gallouëtggml : add fallback definition for HWCAP2_SVE2 (#17683)
2025-12-02 Aleksander... Add context info to server error (#17663)
2025-12-02 Aman Guptaggml-cuda: reorder only relevant nodes (#17639)
2025-12-02 Aaron Teorelease: fix duplicate libs, store symbolic links ...
2025-12-02 Neo Zhang Jianyuenhance argsort for UT (#17573)
2025-12-01 Piotr Wilkin... Override SSM_A op for Qwen3 Next to reduce splits ...
2025-12-01 Jeff Bolzops.md: update vulkan support (#17661)
2025-12-01 Xuan-Son Nguyenmtmd: add mtmd_context_params::warmup option (#17652)
2025-12-01 Gilad S.fix: llama arch implementation (#17665)
2025-12-01 Xuan-Son Nguyenserver: introduce API for serving / loading / unloading...
2025-12-01 Xuan-Son Nguyencommon: improve verbosity level definitions (#17630)
2025-12-01 Xuan-Son Nguyenmodel: support Ministral3 (#17644)
2025-12-01 Georgi Gerganovmetal : add FA head size 48 (#17619)
2025-12-01 Georgi Gerganovggml : extend the GGML_SCHED_NO_REALLOC debug logic...
2025-12-01 Aman Guptallama-graph: avoid expand_forward for fusion (#17633)
2025-11-30 Xuan-Son Nguyencontributing: update guidelines for AI-generated code...
2025-11-30 Adrien Gallouëtcmake : add option to build and link LibreSSL (#17552)
2025-11-30 Tarek Dakhranmodel: LFM2-VL fixes (#17577)
2025-11-30 Xuan-Son Nguyenclip: fix nb calculation for qwen3-vl (#17594)
2025-11-30 Xuan-Son Nguyencli: add migration warning (#17620)
2025-11-30 Adrien Gallouëtcommon : throttle download progress output to reduce...
2025-11-30 Aaron Teocommon: add LLAMA_LOG_FILE env var (#17609)
2025-11-30 Gilad S.ggml: fix: macOS build with `-DGGML_BACKEND_DL=ON`...
2025-11-30 ddh0common: update env var name (#17588)
2025-11-30 Aman GuptaCUDA: add stream-based concurrency (#16991)
2025-11-30 Mahekk Shaikh cuda : add error checking for cudaMemcpyAsync in...
2025-11-30 Aclyvulkan : fix FA mask load with bounds check (coopmat2...
2025-11-29 Xuan-Son Nguyenserver: move server-context to its own cpp|h (#17595)
2025-11-29 Haiyue Wangserver: explicitly set the function name in lambda...
2025-11-29 Igor Smirnovcommon : fix json schema with '\' in literals (#17307)
next