]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-11-05 Georgi Gerganovserver : do not default to multiple slots with speculat...
2025-11-05 Xuan-Son Nguyenmtmd: improve struct initialization (#16981)
2025-11-05 손희준docs: Clarify the endpoint that webui uses (#17001)
2025-11-05 Li Pengzhanmodel : add openPangu-Embedded (#16941)
2025-11-05 Reese Levineggml webgpu: minor set rows optimization (#16810)
2025-11-05 Georgi Gerganovsync : ggml
2025-11-05 Georgi Gerganovggml : fix conv2d_dw SVE path (ggml/1380)
2025-11-05 mnehete32CUDA: update ops.md (#17005)
2025-11-05 lhezopencl: update doc (#17011)
2025-11-04 nullnamerefactor: replace sprintf with snprintf for safer strin...
2025-11-04 Jeff Bolzvulkan: remove the need for the dryrun (#16826)
2025-11-04 Georgi Gerganovserver : do context shift only while generating (#17000)
2025-11-04 Georgi Gerganovreadme : update hot topics (#17002)
2025-11-04 Aclyggml-cpu : bicubic interpolation (#16891)
2025-11-04 Sigbjørn Skjæretci : apply model label to models (#16994)
2025-11-04 Sigbjørn Skjæretchore : fix models indent after refactor (#16992)
2025-11-04 NoahFix garbled output with REPACK at high thread counts...
2025-11-04 Aman GuptaCUDA: avoid mul + bias fusion when doing fusion (#16935)
2025-11-03 lhezopencl: support imrope (#16914)
2025-11-03 Aleksander... fix: Viewing multiple PDF attachments (#16974)
2025-11-03 Daniel Beveniusmodel-conversion : pass config to from_pretrained ...
2025-11-03 Georgi Gerganovserver : add props.model_alias (#16943)
2025-11-03 theo77186ggml: CUDA: add head size 72 for flash-attn (#16962)
2025-11-03 Xuan-Son Nguyenmtmd: add --image-min/max-tokens (#16921)
2025-11-03 Xuan-Son Nguyenmtmd: pad mask for qwen2.5vl (#16954)
2025-11-03 Jinyang Heggml : LoongArch fixes (#16958)
2025-11-03 Olivier Chafiksync: minja (glm 4.6 & minmax m2 templates) (#16949)
2025-11-03 shani-fSYCL: optimized repeat_back kernel (3× fewer asm instru...
2025-11-02 Sascha Rogmannfeat(webui): improve LaTeX rendering with currency...
2025-11-02 Shagun Beratest-backend-ops : fix segfault in moe-expert-reduce...
2025-11-02 Sigbjørn Skjæretci : disable failing riscv cross build (#16952)
2025-11-02 Zhiyong Wangmodel: add Janus Pro for image understanding (#16906)
2025-11-02 Georgi Gerganovclip : use FA (#16837)
2025-11-02 Georgi Gerganovserver : support unified cache across slots (#16736)
2025-11-02 Aldehir Rojascommon : move gpt-oss reasoning processing to init...
2025-11-02 Adrian Lundbergdocs: remove llama_sampler_accept reference in sampling...
2025-11-02 mnehete32CUDA: add FLOOR, CEIL, ROUND, TRUNC unary ops (#16917)
2025-11-02 Aaron Teodevops: fix failing s390x docker build (#16918)
2025-11-02 Aaron Teoggml: add s390x cpu-feats (#16774)
2025-11-01 Georgi Gerganovscripts : add script to bench models (#16894)
2025-11-01 Pascalwebui: auto-refresh /props on inference start to resync...
2025-11-01 Pascalwebui: add HTML/JS preview support to MarkdownContent...
2025-11-01 Adrien Gallouëtvendor : update cpp-httplib to 0.27.0 (#16846)
2025-11-01 Xuan-Son Nguyenmtmd: refactor preprocessing + support max/min pixels...
2025-11-01 Aleksander... Add a setting to display message generation statistics...
2025-11-01 Jaromír Hradílekwebui: recognize AsciiDoc files as valid text files...
2025-11-01 Sigbjørn Skjæretcommon : allow --system-prompt-file for diffusion-cli...
2025-11-01 Sigbjørn Skjæretcodeowners : update after refactor (#16905)
2025-11-01 Jeff Bolzvulkan: Fix multi_add invalid descriptor usage (#16899)
2025-11-01 Jeff Bolzvulkan: fuse mul_mat+add and mul_mat_id+add_id (#16868)
2025-11-01 Oliver SimonsCUDA: Remove unneded bias/gate dims in fused mmvq ...
2025-10-31 Piotr Wilkin... refactor : llama-model.cpp (#16252)
2025-10-31 Piotr Wilkin... model : Minimax M2 (#16831)
2025-10-31 Giuseppe Scrivanomodel : add Granite Hybrid nano types (#16896)
2025-10-31 Johannes GäßlerCUDA: Volta tensor core support for MMF (#16843)
2025-10-31 Georgi Gerganovsync : ggml
2025-10-31 Aman GuptaCUDA: add expert reduce kernel (#16857)
2025-10-31 Georgi Gerganovbatch : fix consistency checks for the input positions...
2025-10-31 Georgi Gerganovserver : don't print user inputs to console (#16871)
2025-10-31 Daniel Beveniusserver : fix typos in server.cpp comments [no ci] ...
2025-10-31 Jeff Bolzvulkan: disable spirv-opt for rope shaders (#16872)
2025-10-31 Masato Nakasakavulkan: Fix crash when FP16 mul_mat accumulation is...
2025-10-31 Ruben Ortlamvulkan: fix shmem overrun in mmq id shader (#16873)
2025-10-31 l3utterflyggml-hexagon: respect input size when getting/setting...
2025-10-30 Sigbjørn Skjæretci : enable free-disk-space on cuda docker build (...
2025-10-30 lhezopencl: fix boundary handling for mul_mm (#16875)
2025-10-30 RodriMoraconvert : update transformers requirements (#16866)
2025-10-30 chansikparkserver : bump request URI max length to 32768 (#16862)
2025-10-30 Georgi Gerganovserver : remove n_past (#16818)
2025-10-30 Max Krasnyanskycpu: introduce chunking for repack matmuls and enable...
2025-10-30 Shagun Beracommon: fix typo in cli help text (#16864)
2025-10-30 JJJYmmmmodel: add support for qwen3vl series (#16780)
2025-10-30 Max Krasnyanskycpu: introduce chunking for flash attention (#16829)
2025-10-30 Tianyue-Zhaomodel: Add support for CogVLM model (#15002)
2025-10-30 Sigbjørn Skjæretcuda : fix argsort with 64k+ rows (#16849)
2025-10-30 Jan Boonllama : use std::abs instead of abs (#16853)
2025-10-30 Jeff Bolzvulkan: Handle argsort with a large number of rows...
2025-10-30 Oliver SimonsHide latency of bias and gate-loading (#16847)
2025-10-29 Jeff Bolzvulkan: Fuse rope+set_rows (#16769)
2025-10-29 Xuan-Son Nguyenllama: fix ASAN error with M-RoPE (#16848)
2025-10-29 Xuan-Son Nguyenllama: store mrope data in KV cell (#16825)
2025-10-29 Jeff Bolzvulkan: Update topk_moe fusion to handle gpt's late...
2025-10-29 Ruben OrtlamVulkan MMQ Integer Dot Refactor and K-Quant support...
2025-10-29 Max KrasnyanskyHexagon Op queue & dispatch optimizations (#16820)
2025-10-29 Aman GuptaCUDA: use fastdiv in set-rows (#16834)
2025-10-29 Sigbjørn Skjæretvendor : sync minja (#16500)
2025-10-29 Jeff Bolzvulkan: Call ggml_vk_buffer_write_2d from ggml_vk_buffe...
2025-10-29 Aman GuptaCUDA: Fix bug in topk-moe for gpt-oss (#16821)
2025-10-29 YaelLogicsycl: add RMS_NORM_BACK operation support (#16808)
2025-10-28 YaelGitAccountcuda: add SET operation support (#16804)
2025-10-28 Georgi Gerganovmemory : remove KV cache size padding (#16812)
2025-10-28 Georgi Gerganovllama-bench : clarify benchmarked parts of the computat...
2025-10-28 l3utterflyinitialise buffer.device in ggml_hexagon_session (...
2025-10-28 Sam Malayekembedding: add raw option for --embd-output-format...
2025-10-28 Johannes Gäßlerllama: consistent ctx <-> buf order for KV cache (...
2025-10-28 Aldehir Rojasgrammar : support array references in json schema ...
2025-10-28 Chenguang LiCANN: Improve device ID handling and aclnnArange checks...
2025-10-28 Aman GuptaCUDA: add unused vars to mmvf and mmvq (#16807)
2025-10-28 tamarPalsycl: add SSM_CONV operation support (#16800)
2025-10-27 Yuri Khrustalevchat: Add LFM2 tool handling (#16763)
next