]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-06-26 Georgi Gerganovmetal : batch rows copy in a single threadgroup (#14384)
2025-06-26 Aaron Teodocs: update s390x documentation + add faq (#14389)
2025-06-26 R0CKSTARmusa: enable fp16 mma (all) and cublas on qy2 (#13842)
2025-06-25 Aaron Teoggml-cpu: enable IBM NNPA Vector Intrinsics (#14317)
2025-06-25 Sigbjørn Skjæretggml : do not output unprintable characters on GGUF...
2025-06-25 Anton Mitkovsycl: GGML_SYCL_DISABLE_OPT on by default for all Intel...
2025-06-24 lhezopencl: ref count `ggml_backend_opencl_context` and...
2025-06-24 Georgi Gerganovbatch : fix check for empty sequences in memory (#14364)
2025-06-24 Mathieu Baudiercmake : use LLAMA_BUILD_NUMBER when defining LLAMA_INST...
2025-06-24 Nigel Boschserver : move no API key doc to /health (#14352)
2025-06-24 Sigbjørn Skjæretmain : honor --verbose-prompt on interactive prompts...
2025-06-24 Bartowskijinja : Add Mistral-Small-3.2-24B-Instruct-2506.jinja...
2025-06-23 uvosCUDA/HIP: optimize mmv paths taken for HIP devices...
2025-06-23 bandotici: add workflow for relocatable cmake package (#14346)
2025-06-23 Jeff Bolzvulkan: update windows SDK in release.yml (#14344)
2025-06-23 Molly Sophiallama : better rwkv chat template and add missing ...
2025-06-23 Johannes GäßlerCUDA: mul_mat_v support for batch sizes > 1 (#14262)
2025-06-23 Georgi Gerganovkv-cells : fix tracking of seq_pos (#14339)
2025-06-23 Jeff Bolzvulkan: update windows SDK in CI (#14334)
2025-06-22 Ed Addarioquantize : handle user-defined pruning of whole layers...
2025-06-22 Sigbjørn Skjæretgguf-py : fix SpecialVocab parsing when post_processor...
2025-06-22 Ruikai Pengrun : avoid double tokenization (#14327)
2025-06-22 Georgi Gerganovexamples : fix is_first logic for tokenization (#14329)
2025-06-22 uvosHIP: enable vec fattn on RDNA4 (#14323)
2025-06-22 yuisekimtmd : fix Pixtral OOM with large images by capping...
2025-06-22 Sigbjørn Skjæretcommon : use std::string_view now that we target c...
2025-06-22 Aman GuptaCUDA: add mean operation (#14313)
2025-06-21 Sigbjørn Skjæretgguf-py : fix Qwen3-Embedding eos token (#14314)
2025-06-21 Markus TavenrathAdd support for VK_EXT_debug_utils to add labels to...
2025-06-21 Sigbjørn Skjæretgguf-py : fix TemplateProcessing pair when bos/eos...
2025-06-21 Georgi Gerganovmetal : fix thread-safety (#14300)
2025-06-21 Georgi Gerganovmemory : rename interface to llama_memory_context_i...
2025-06-21 Daniel Hanconvert : fix Llama 4 conversion (#14311)
2025-06-20 Georgi Gerganovsync : ggml
2025-06-20 AclyAdd `ggml_roll` (ggml/1274)
2025-06-20 David Chiudocs : fix the link to llama.h (#14293)
2025-06-20 Aman GuptaCUDA: add conv_2d_transpose (#14287)
2025-06-20 Sigbjørn Skjæretlint : remove trailing whitepace (#14304)
2025-06-20 Ruikai Pengvocab : prevent tokenizer overflow (#14301)
2025-06-20 Nicolò Scipionesycl: add usage of enqueue_functions extension (#14244)
2025-06-20 Christian KastnerImplement GGML_CPU_ALL_VARIANTS for PowerPC (#14286)
2025-06-20 Sigbjørn Skjæretllama : improve sep token handling (#14272)
2025-06-20 Diego Devesacuda : synchronize graph capture and cublas handle...
2025-06-20 Georgi Gerganovggml : fix repack work size for mul_mat_id (#14292)
2025-06-20 Charles Xuggml: Update KleidiAI to v1.9.0 (#14277)
2025-06-20 Georgi Gerganovmodel : more uniform output id handling (#14275)
2025-06-20 Georgi Gerganovubatch : new splitting logic (#14217) upstream/0.0.5713
2025-06-20 Aman GuptaCUDA: add conv_2d_dw (#14265)
2025-06-19 Diego Devesaggml-cpu : remove unnecesary arm feature detection...
2025-06-19 Alex Trottagguf-py : make sentencepiece optional (#14200) gguf-v0.17.1
2025-06-19 aa956server : add server parameters for draft model cache...
2025-06-19 fanyangbuild : suppress gcc15 compile warnings (#14261)
2025-06-19 Anton Mitkovsycl: Cleanup codepaths in Get Rows in sycl backend...
2025-06-19 bashayer hijjillama-bench : add --no-warmup flag (#14224) (#14270)
2025-06-19 pqnetconvert : fix remote option in Windows (#14100)
2025-06-19 Aaron Teollamafile : support s390x SIMD instruction set (#14273)
2025-06-19 0cc4mVulkan: Set device max size for host memory to avoid...
2025-06-19 Gabe Goodhartmemory : Hybrid recurrent cache (#13979)
2025-06-19 Georgi Gerganovmetal : add mean kernel (#14267)
2025-06-18 Aaron Teodocs: add s390x build documentation (#14264)
2025-06-18 Aaron Teoggml-cpu: reduce asm calls for hsum (#14037)
2025-06-18 Aaron Teoggml-cpu: fix uncaught underscore terminators (#14023)
2025-06-18 Charles Xuggml: Add Apple support for GGML_CPU_ALL_VARIANTS ...
2025-06-18 Xuan-Son Nguyenmtmd : refactor llava-uhd preprocessing logic (#14247)
2025-06-18 Xuan-Son Nguyenllama-chat : fix multiple system message for gemma...
2025-06-18 Sigbjørn Skjæretconvert : fix null head_dim AutoConfig regression ...
2025-06-18 Georgi Gerganovsync : ggml
2025-06-18 Daniel Beveniusggml : disable warnings for tests when using MSVC ...
2025-06-18 Daniel Beveniusggml : remove unused ggml_context_container (ggml/1272)
2025-06-18 Daniel Beveniusexamples : include examples in msvc disable warn (ggml...
2025-06-17 bandoticmake: remove shader-gen step-targets from ggml-vulkan...
2025-06-17 xctanggml-cpu : remove the weak alias trick (#14221)
2025-06-17 R0CKSTARmusa: fix build warning (unused variable) (#14231)
2025-06-16 Sigbjørn Skjæretcommon : suggest --jinja when autodetection fails ...
2025-06-16 Georgi Gerganovserver : fix incorrect usage of llama_get_embeddings...
2025-06-16 Diego Devesallama : add thread safety test (#14035)
2025-06-16 bandoticmake: clean up external project logic for vulkan-shade...
2025-06-16 Đinh Trọng Huymodel : add NeoBERT (#14164)
2025-06-16 uvosHIP: disable rocwmma on gfx12 by default until rocm...
2025-06-16 Georgi Gerganovllama : rework embeddings logic (#14208)
2025-06-16 Charles Xuggml: Add Android support for GGML_CPU_ALL_VARIANTS...
2025-06-16 Bartowskiconvert : remove arcee change in convert_hf_to_gguf_upd...
2025-06-16 Đinh Trọng Huygguf-py : allow key override when adding value to GGUFW...
2025-06-16 Jeff Bolzvulkan: mutex around vkQueueSubmit (#14127)
2025-06-16 xctanggml-cpu : rework weak alias on apple targets (#14146)
2025-06-15 Bartowskimodel : Add support for Arcee AI's upcoming AFM model...
2025-06-15 Eric Curtinserver : When listening on a unix domain socket don...
2025-06-15 Ed Addarioquantize : change int to unsigned int for KV overrides...
2025-06-15 uvosCUDA/HIP: fix ssm_scan on devices where warp size is...
2025-06-15 uvosHIP: Replace usage of depricated preprocessor macro...
2025-06-15 Georgi Gerganovkv-cache : fix use-after-move of defrag info (#14189)
2025-06-15 Mikko Juolamodel : add dots.llm1 architecture support (#14044...
2025-06-15 Georgi Gerganovcparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_...
2025-06-15 Georgi Gerganovbatch : auto-gen positions + verify multi-sequence...
2025-06-15 Pepijn de Vosdocs : remove WIP since PR has been merged (#13912)
2025-06-14 Piotrllama-chat : Do not throw when tool parsing fails ...
2025-06-14 Aman Guptacompare-llama-bench: add option to plot (#14169)
2025-06-13 Georgi Gerganovvocab : fix build (#14175)
2025-06-13 Svetlozar Georgievsycl: fix docker image (#14144)
2025-06-13 Guy GoldenbergMerge commit from fork
next