]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-02-03 Olivier Chafik`tool-call`: allow `--chat-template chatml` w/ `--jinja...
2025-02-03 Xuan-Son Nguyenserver : (webui) revert hacky solution from #11626...
2025-02-03 Woof Dogserver : (webui) allow typing and submitting during...
2025-02-03 Daniel Beveniusserver : remove CPPHTTPLIB_NO_EXCEPTIONS define (#11622)
2025-02-03 Georgi Gerganovsync : ggml
2025-02-03 Johannes GäßlerCUDA: fix Volta FlashAttention logic (#11615)
2025-02-03 mashdragonserver : (webui) Fix Shift+Enter handling (#11609)
2025-02-02 Johannes GäßlerHIP: fix flash_attn_stream_k_fixup warning (#11604)
2025-02-02 uvosCUDA/HIP: add support for selectable warp size to mmv...
2025-02-02 uvosHIP: add GGML_CUDA_CC_IS_* for amd familys as increasin...
2025-02-02 Olivier Chafiknit: more informative crash when grammar sampler fails...
2025-02-02 Johannes GäßlerCUDA: use mma PTX instructions for FlashAttention ...
2025-02-02 Eric CurtinName colors (#11573)
2025-02-02 Olivier Chafik`tool-call`: support Command R7B (+ return tool_plan...
2025-02-02 Olivier ChafikFix exotic ci env that lacks ostringstream::str (#11581)
2025-02-02 Michał Moskalsampling : support for llguidance grammars (#10224)
2025-02-02 piDackllama : add support for GLM-Edge and GLM-Edge-V series...
2025-02-01 Olivier Chafikci: use sccache on windows HIP jobs (#11553)
2025-02-01 Olivier Chafik`sync`: minja (https://github.com/google/minja/commit...
2025-02-01 Eric CurtinImplement s3:// protocol (#11511)
2025-02-01 Olivier Chafikci: simplify cmake build commands (#11548)
2025-01-31 Olivier Chafik`ci`: use sccache on windows instead of ccache (#11545)
2025-01-31 Olivier Chafik`tool-call`: fix llama 3.x and functionary 3.2, play...
2025-01-31 Olivier Chafikfix stop regression (#11543)
2025-01-31 Olivier ChafikFix chatml fallback for unsupported builtin templates...
2025-01-31 Olivier Chafikserver : fix --jinja when there's no tools or schema...
2025-01-31 Steve Grubbcommon: Add missing va_end (#11529)
2025-01-31 Daniel Beveniusserver : update help metrics processing/deferred (...
2025-01-30 Olivier Chafik`ci`: ccache for all github worfklows (#11516)
2025-01-30 Olivier ChafikTool call support (generic + native for Llama, Function...
2025-01-30 uvosHIP: require at least HIP 5.5
2025-01-30 uvosHIP: Prepare reduction operators for wave 64
2025-01-30 uvosCUDA/HIP: add warp_size to cuda_device_info
2025-01-30 Olivier Chafiksync: minja (#11499)
2025-01-30 mgroeber9110vocab : correctly identify LF token for GPT-2 style...
2025-01-30 Daniel Beveniusserver : use lambda instead of std::bind (#11507)
2025-01-30 Isaac McFadyenserver : (docs) added response format for /apply-templa...
2025-01-30 Guspan Tanadireadme : reference examples relative links (#11505)
2025-01-30 Daniel Beveniusserver : update json snippets in README.md [no ci]...
2025-01-29 Nigel Boschserver : add /apply-template endpoint for additional...
2025-01-29 Rémy Oudomphengvulkan: implement initial support for IQ2 and IQ3 quant...
2025-01-29 Daniel Beveniusserver : update auto gen files comments [no ci] (#11484)
2025-01-29 Jeff Bolzvulkan: Catch pipeline creation failure and print an...
2025-01-29 Eric CurtinParse https://ollama.com/library/ syntax (#11480)
2025-01-29 Georgi Gerganovsync : ggml
2025-01-29 William Tambelliniggml : add option to not print stack on abort (ggml...
2025-01-29 issixxggml-cpu : fix ggml_graph_compute_thread did not termin...
2025-01-29 Daniel Beveniusembedding : enable --no-warmup option (#11475)
2025-01-29 Molly Sophiallama: fix missing k_cache store for rwkv6qwen2 (#11445)
2025-01-28 Emreerdogcmake: add hints for locating ggml on Windows using...
2025-01-28 peidaqiserver : Fixed wrong function name in llamacpp server...
2025-01-28 Xuan-Son Nguyenci : fix build CPU arm64 (#11472)
2025-01-28 uvosHIP: Supress transformation warning in softmax.cu
2025-01-28 Nikita SarychevHIP: Only call rocblas_initialize on rocblas versions...
2025-01-28 Eric CurtinAdd github protocol pulling and http:// (#11465)
2025-01-28 Nunodocker: allow installing pip packages system-wide ...
2025-01-28 someone13574cmake : don't fail on `GGML_CPU=OFF` (#11457)
2025-01-28 Nunodocker: add perplexity and bench commands to full image...
2025-01-28 Akarshan BiswasSYCL : SOFTMAX F16 mask support and other fixes (#11261)
2025-01-28 Michael EngelHandle missing model in CLI parameters for llama-run...
2025-01-27 Eric CurtinAdd new hf protocol for ollama (#11449)
2025-01-27 Haus1AMD: parse the architecture as supplied by gcnArchName...
2025-01-27 lexasubllama : minor fixes for up llama load model speed ...
2025-01-27 Johannes Gäßlerllama: refactor llama_decode_impl (#11381)
2025-01-27 Ihar Hrachyshkametal: Handle null returned from MTLCreateSystemDefault...
2025-01-26 Xuan Son Nguyendocker : fix ARM build and Vulkan build (#11434)
2025-01-26 Georgi Gerganovmetal : use residency sets (#11427)
2025-01-26 Nunodocker: add missing vulkan library to base layer and...
2025-01-26 bandoticmake: add ggml find package (#11369)
2025-01-26 Frank Mairpc: fix register position (#11424)
2025-01-26 Georgi Gerganovreadme : update hot topics
2025-01-26 Jeff Bolzbuild: apply MSVC /bigobj option to c/cpp files only...
2025-01-25 Jeff Bolzvulkan: compile shaders on-demand (#11406)
2025-01-25 uvosHip: disable VMM on hip as it seams that it dosent...
2025-01-25 Jeff Bolzbuild: add /bigobj to MSVC build (#11407)
2025-01-25 Diego Devesadocker : add GGML_CPU_ARM_ARCH arg to select ARM archit...
2025-01-25 Xuan Son Nguyenserver : fix cleaning up stream task (#11418)
2025-01-25 Diego Devesadocker : fix CPU ARM build (#11403)
2025-01-25 Georgi Gerganovci : fix line breaks on windows builds (#11409)
2025-01-24 jiahao suCANN: Add Ascend CANN build ci (#10217)
2025-01-24 uvoship : Add hipGraph and VMM support to ROCM (#11362)
2025-01-24 Johannes GäßlerCUDA: fix FP16 cuBLAS GEMM (#11396)
2025-01-24 uvosrocBLAS: Avoid fp32->fp16->fp32 conversion on cdna...
2025-01-24 Georgi Gerganovrelease : pack /lib in the packages (#11392)
2025-01-24 Jafar Uruçdocs : Update readme to build targets for local docker...
2025-01-24 Johannes GäßlerCPU/CUDA: fix (GQA) mul mat back, add CUDA support...
2025-01-24 Bernhard M... cmake : avoid -march=native when reproducible build...
2025-01-24 Eric CurtinUpdate llama-run README.md (#11386)
2025-01-24 stduhpfserver : (webui) put DeepSeek R1 CoT in a collapsible...
2025-01-23 Jeff Bolztests: fix some mul_mat test gaps (#11375)
2025-01-23 Eric CurtinUpdate documentation (#11373)
2025-01-23 Eric CurtinAdd -ngl (#11372)
2025-01-23 Xuan Son Nguyenserver : add more clean up when cancel_tasks is called...
2025-01-23 Eric CurtinTreat hf.co/ prefix the same as hf:// (#11350)
2025-01-23 amd-dwangVulkan-run-test: fix mmq_wg_denoms (#11343)
2025-01-23 Jeff Bolzvulkan: sort shaders for more deterministic binary...
2025-01-23 Jeff Bolzvulkan: fix diag_mask_inf (#11323)
2025-01-22 Diego Devesamain : update README documentation for batch size ...
2025-01-22 Georgi Gerganovreadme : add plugin links (#11355)
2025-01-22 Diego Devesaserver : fix draft context not being released (#11354)
next