]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
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)
2025-01-22 Olivier Chafik`minja`: sync at https://github.com/google/minja/commit...
2025-01-22 Jiří PodivínAdding logprobs to /v1/completions (#11344)
2025-01-22 Olivier Chafik`common`: utils to split / join / repeat strings (from...
2025-01-22 tc-mbllava : support Minicpm-omni (#11289)
2025-01-21 Olivier ChafikAdd Jinja template support (#11016)
2025-01-21 Xuan Son Nguyenexport-lora : fix tok_embd tensor (#11330)
2025-01-21 Radoslav Gerganovrpc : better caching of the base buffer pointer (#11331)
2025-01-21 Eric Curtinlinenoise.cpp refactoring (#11301)
2025-01-21 Georgi Gerganovmetal : fix out-of-bounds write (#11314)
2025-01-20 Georgi Gerganovcommon : add -hfd option for the draft model (#11318)
2025-01-20 Jeff Bolzvulkan: fix coopmat2 validation failures (#11284)
2025-01-20 Georgi Gerganovexamples : fix add_special conditions (#11311)
2025-01-20 Christopher... mmap: add include for cerrno (#11296)
2025-01-20 Michael Podvitskiycmake: fix shell command quoting in build-info script...
2025-01-20 Xuan Son Nguyenllama : add support for Deepseek-R1-Qwen distill model...
2025-01-20 Georgi Gerganovcont : fix whitespaces (#11305)
2025-01-20 Kyle Bruenellama : re-add LLM_ARCH_PHIMOE (#11305)
2025-01-19 Georgi Gerganovtests : increase timeout when sanitizers are enabled...
2025-01-19 Georgi Gerganovsimple-chat : fix BOS being added to each message ...
2025-01-19 Nicolò ScipioneSYCL: Introducing memory host pool (#11251)
2025-01-18 Eric CurtinAdding linenoise.cpp to llama-run (#11252)
2025-01-18 Georgi Gerganovcmake : add sanitizer flags for llama.cpp (#11279)
2025-01-18 Xuan Son Nguyenserver : implement cancellable request (#11285)
2025-01-18 Georgi Gerganovscripts : restore hf.sh (#11288)
2025-01-18 LostRuins Concedotts : add guide tokens support (#11186)
2025-01-18 Jeff Bolzvulkan: fix coopmat2 flash attention for non-contiguous...
2025-01-17 codezjxllama.android: add field formatChat to control whether...
2025-01-17 Radoslav Gerganovrpc : early register backend devices (#11262)
2025-01-17 Georgi Gerganovvocab : fix double-eos check (#11273)
2025-01-17 David Renshawllama : fix deprecation message: vocabable -> vocab...
2025-01-17 musolesREADME : added kalavai to infrastructure list (#11216)
2025-01-16 Jeff Bolzvulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1...
2025-01-16 Jeff Bolzvulkan: optimize coopmat2 q4_k/q5_k dequant functions...
2025-01-16 Jeff Bolzvulkan: optimize coopmat2 q2_k dequant function (#11130)
2025-01-16 RunningLeonllama : add internlm3 support (#11233)
2025-01-16 Johannes GäßlerCUDA: backwards pass for misc. ops, add tests (#11257)
2025-01-16 Xuan Son Nguyenllama : add `llama_model_load_from_splits` (#11255)
2025-01-16 fj-y-saitoggml: aarch64: implement SVE kernels for q4_K_q8_K...
2025-01-15 Evevulkan: scale caching for k quants + misc fixes (#11081)
2025-01-15 Georgi Gerganovci : use -no-cnv in gguf-split tests (#11254)
2025-01-15 Junil Kimfix: ggml: fix vulkan-shaders-gen build (#10448) upstream/0.0.4488
2025-01-15 Johannes GäßlerRoPE: fix back, CUDA support for back + noncont. (...
2025-01-15 Daniel Beveniusexamples : add embd_to_audio to tts-outetts.py [no...
2025-01-15 Akarshan BiswasSYCL: Add gated linear attention kernel (#11175)
2025-01-14 Xuan Son Nguyenci : add -no-cnv for tests (#11238)
2025-01-14 Georgi Gerganovvocab : add dummy tokens for "no_vocab" type (#11231)
2025-01-14 ebraminioserver : Improve code snippets direction between RTL...
2025-01-14 Olivier ChafikRefactor test-chat-template.cpp (#11224)
2025-01-14 Georgi Gerganovsync : ggml
2025-01-14 Georgi Gerganovscripts : sync gguf (cont)
2025-01-14 Georgi Gerganovscripts : sync gguf
2025-01-14 Georgi Gerganovscripts : sync opencl
2025-01-13 ebraminioserver : (UI) Improve messages bubble shape in RTL...
2025-01-13 Xuan Son Nguyencli : auto activate conversation mode if chat template...
2025-01-13 Andreas Kieslingercuda : CUDA Graph Compute Function Refactor (precursor...
2025-01-13 Georgi Gerganovcontrib : add naming guidelines (cont) (#11177)
2025-01-13 ebraminioserver : (UI) Support for RTL text as models input...
2025-01-13 Georgi Gerganovcontrib : add naming guidelines (cont) (#11177)
2025-01-13 Xuan Son Nguyencommon : support tag-based --hf-repo like on ollama...
2025-01-13 Georgi Gerganovcontrib : add naming guidelines (#11177)
2025-01-13 Daniel Beveniusllama : remove 'd' from bad special token log (#11212)
2025-01-13 Radoslav Gerganovggml : do not define GGML_USE_CUDA when building with...
2025-01-12 Eric CurtinReset color before we exit (#11205)
2025-01-12 Xuan Son Nguyenllama : fix chat template gguf key (#11201)
2025-01-12 Georgi Gerganovllama : remove notion of CLS token (#11064)
2025-01-12 Georgi Gerganovllama : add `llama_vocab`, functions -> methods, naming...
2025-01-11 Vinesh Janarthanangguf-py: fixed local detection of gguf package (#11180)
2025-01-11 Daniel Beveniusconvert : sort print supported models [no ci] (#11179)
2025-01-10 Daniel Beveniusexamples : add README.md to tts example [no ci] (#11155)
2025-01-10 Daniel Beveniusconvert : add --print-supported-models option (#11172)
2025-01-10 0cc4mVulkan: Fix float16 use on devices without float16...
2025-01-10 Molly Sophiallama: add support for QRWKV6 model architecture (...
2025-01-10 Akarshan BiswasSYCL: Refactor ggml_sycl_compute_forward (#11121)
2025-01-09 Tei Homedoc: add cuda guide for fedora (#11135)
2025-01-09 Daniel Beveniusserver : add tooltips to settings and themes btn (...
next