]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2024-12-21 Georgi Gerganovconvert : add BertForMaskedLM (#10919)
2024-12-21 Jeff Bolzvulkan: optimize coopmat2 dequant functions (#10855)
2024-12-20 Adrien Gallouëtggml-cpu: replace NEON asm with intrinsics in ggml_gemv...
2024-12-20 Akarshan BiswasSYCL: Migrate away from deprecated ggml_tensor->backend...
2024-12-20 Xuan Son Nguyenserver : (UI) fix copy to clipboard function (#10916)
2024-12-20 Diego Devesaggml : add test for SVE and disable when it fails ...
2024-12-20 Molly Sophiaconvert : fix RWKV v6 model conversion (#10913)
2024-12-19 Georgi Gerganovclip : disable GPU support (#10896)
2024-12-19 Georgi Gerganovllama : minor grammar refactor (#10897)
2024-12-19 Georgi Gerganovtts : small QoL for easy model fetch (#10903)
2024-12-19 Xuan Son Nguyenserver : fix logprobs, make it OAI-compatible (#10783)
2024-12-19 Adrien Gallouëtggml: fix arm build with gcc (#10895)
2024-12-19 Sukriti Sharmallama : fix Roberta embeddings (#10856)
2024-12-19 fairydreamingconvert : Add support for Microsoft Phi-4 model (...
2024-12-19 Johannes Gäßlertests: disable GGUF test for bad value size (#10886)
2024-12-19 Eric Curtinllama-run : improve progress bar (#10821)
2024-12-18 Diego Devesaggml : fix arm build (#10890)
2024-12-18 Georgi Gerganovtts : add OuteTTS support (#10784)
2024-12-18 Gaetan Bissonserver: avoid overwriting Authorization header (#10878)
2024-12-18 Georgi Gerganovserver : output embeddings for all tokens when pooling...
2024-12-18 Georgi Gerganovserver : add "tokens" output (#10853)
2024-12-18 Xuan Son Nguyenserver : (embeddings) using same format for "input...
2024-12-18 redbearddocs: Fix HIP (née hipBLAS) in README (#10880)
2024-12-18 Diego DevesaRevert "llama : add Falcon3 support (#10864)" (#10876)
2024-12-17 DAN™Use model->gguf_kv for loading the template instead...
2024-12-17 Johannes Gäßlertests: add tests for GGUF (#10830)
2024-12-17 Georgi Gerganovsync : ggml
2024-12-17 Georgi Gerganovcmake : fix "amd64" processor string (whisper/2638)
2024-12-17 gn64vulkan : fix soft_max.comp division by zero (whisper...
2024-12-17 Daniel Beveniusggml : remove return from ggml_gallocr_allocate_node...
2024-12-17 Daniel Beveniusggml : add check for grad_accs (ggml/1046)
2024-12-17 Georgi Gerganovggml : update ggml_backend_cpu_device_supports_op ...
2024-12-17 krystianchaserver : fill usage info in embeddings and rerank respo...
2024-12-17 Billel Mokeddemllama : add Falcon3 support (#10864)
2024-12-17 Ruanreadme : update typos (#10863)
2024-12-17 Xuan Son Nguyenserver : (UI) fix missing async generator on safari...
2024-12-17 Evevulkan: bugfixes for small subgroup size systems +...
2024-12-16 Zhiyuan Lirwkv6: add wkv6 support for Vulkan backend (#10829)
2024-12-16 Georgi Gerganovunicode : improve naming style (#10838)
2024-12-16 Georgi Gerganovsampling : refactor + optimize penalties sampler (...
2024-12-15 Bartowskillava : Allow locally downloaded models for QwenVL...
2024-12-15 Valentin Mamedovllama : add Deepseek MoE v1 & GigaChat models (#10827)
2024-12-15 Georgi Gerganovscripts : change build path to "build-bench" for compar...
2024-12-15 Vinesh Janarthananserver: (UI) add syntax highlighting and latex math...
2024-12-15 Georgi Gerganovgguf-py : bump to v0.13.0
2024-12-14 Michelle Tanserver: Fix `has_next_line` in JSON response (#10818)
2024-12-14 Evgeny Kurnevskynix: allow to override rocm gpu targets (#10794)
2024-12-14 HimariOllama : add Qwen2VL support + multimodal RoPE (#10361)
2024-12-13 cdukRemoves spurious \r in output that causes logging in...
2024-12-13 lhezIntroducing experimental OpenCL backend with support...
2024-12-13 Eric CurtinOpt class for positional argument handling (#10508)
2024-12-13 Corentin REGALfix: graceful shutdown for Docker images (#10815)
2024-12-13 Jett Janiakgguf-py : numpy 2 newbyteorder fix (#9772)
2024-12-13 谢乃闻Fix crash caused by ggml_backend_load_all when launchin...
2024-12-13 Evevulkan: small mul_mat_vec optimizations (#10665)
2024-12-13 Akarshan BiswasSYCL: Reduce most of the compiler warnings (#10748)
2024-12-13 Karol Kontnyggml : Fix compilation issues on ARM platform when...
2024-12-12 Xuan Son Nguyencommon : improve -ctv -ctk CLI arguments (#10806)
2024-12-12 Xuan Son Nguyencontrib : add ngxson as codeowner (#10804)
2024-12-12 a3shCUDA: faster non-contiguous concat (#10760)
2024-12-12 Diego Devesaremove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
2024-12-12 0cc4mVulkan: Use improved q4_k and q5_k dequant code in...
2024-12-12 0cc4mVulkan: Add VK_EXT_subgroup_size_control support to...
2024-12-12 Xuan Son Nguyencommon : add missing env var for speculative (#10801)
2024-12-11 CentricStormdocs: update server streaming mode documentation (...
2024-12-11 Georgi GerganovMerge pull request #10788 from ggerganov/gg/gguf-py...
2024-12-11 Georgi Gerganovgguf-py : bump version to 0.11.0
2024-12-11 Xuan Son Nguyenserver : (UI) add tok/s, get rid of completion.js ...
2024-12-11 qingy1337Update README.md (#10772)
2024-12-11 Xuan Son Nguyenci : pin nodejs to 22.11.0 (#10779)
2024-12-11 kallewoofbug-fix: snprintf prints NULL in place of the last...
2024-12-11 CentricStormdocs: fix server documentation formatting (#10776)
2024-12-11 Gilad S.ggml: load all backends from a user-provided search...
2024-12-10 Jeff Bolzvulkan: request round-to-even for fp16 in im2col/rope_h...
2024-12-10 Evevulkan: dynamic subgroup size for the remaining k quant...
2024-12-10 Bartowskiimatrix : Add imatrix to --no-context-shift (#10766)
2024-12-10 Andreas KieslingerCUDA: rename macros to avoid conflicts with WinAPI...
2024-12-10 Yügserver : add flag to disable the web-ui (#10762) (...
2024-12-10 Jeff Bolzvulkan: disable spirv-opt for coopmat shaders (#10763)
2024-12-09 Johannes GäßlerCUDA: fix shared memory access condition for mmv (...
2024-12-09 Srihari-mcwChanges to CMakePresets.json to add ninja clang target...
2024-12-09 Jeff Bolzvulkan: fix compile warnings (#10731)
2024-12-09 Borislav Stanimirovcmake : simplify msvc charsets (#10672)
2024-12-08 Xuan Son Nguyenserver : fix format_infill (#10724)
2024-12-08 Xuan Son Nguyenserver : bring back info of final chunk in stream mode...
2024-12-08 stduhpfVulkan: fix NaN in tanh.comp with AMD proprietary drive...
2024-12-08 Diego Devesallama : use cmake for swift build (#10525)
2024-12-08 Jeff Bolzvulkan: compile a test shader in cmake to check for...
2024-12-07 Robert Collinsllama : add 128k yarn context for Qwen (#10698)
2024-12-07 Xuan Son Nguyenserver : (refactor) no more json in server_task input...
2024-12-07 Georgi Gerganovggml : disable iq4_nl interleave size 8 (#10709)
2024-12-07 Georgi Gerganovserver : various fixes (#10704)
2024-12-07 Djip007ggml : refactor online repacking (#10446)
2024-12-07 Georgi Gerganovserver : fix free of spec context and batch (#10651)
2024-12-07 0cc4mVulkan: VK_KHR_cooperative_matrix support to speed...
2024-12-07 Robert Ormandimetal : Extend how Llama.cpp locates metal resources...
2024-12-07 Sukriti Sharmaconvert : add support for Roberta embeddings (#10695)
2024-12-06 Georgi Gerganovconvert : add custom attention mapping
2024-12-06 Xuan Son Nguyencommon : bring back --no-warmup to server (#10686)
2024-12-06 Xuan Son Nguyenserver : (refactoring) do not rely on JSON internally...
next