]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-05-12 Jeff Bolzvulkan: Check shared memory size for mmq shaders (...
2026-05-12 Sigbjørn Skjæretci : bump ty to 0.0.35 (#22961)
2026-05-12 AesSedaimtmd: add MiMo v2.5 vision (#22883)
2026-05-12 Jesus Talaveraconvert : add split() to LoraTorchTensor in LoRA conver...
2026-05-12 guyfischmanmetal : promote mul_mv/mul_mm batch divisors to functio...
2026-05-11 Shawn Guopencl: add q4_1 MoE for Adreno (#22856)
2026-05-11 CrispStrobeCUDA: handle OW > 65535 in im2col (2D and 3D) (#22944)
2026-05-11 PascalGgml/cuda snake fusion hardening (#22912)
2026-05-11 willjohadocs: fix metrics endpoint description in server README...
2026-05-11 Georgi Gerganovspec : parallel drafting support (#22838)
2026-05-11 Kevin Pougetggml-virtgpu: Add a GHA build check (#22943)
2026-05-11 Daniel Beveniusexamples : update args speculative-simple README.md...
2026-05-11 Jeff Bolzvulkan: Support asymmetric FA in scalar/mmq/coopmat1...
2026-05-11 Oliver SimonsCUDA: directly include cuda/iterator (#22936)
2026-05-11 Daniel Beveniusconvert : add image break token fallback (#22914)
2026-05-11 Alessandro... vendor : update cpp-httplib to 0.44.0 (#22919)
2026-05-11 Neo Zhang[SYCL] Add OP im2col_3d (#22903)
2026-05-10 Georgi Gerganovserver : print warning when HTTP timeout exceeded ...
2026-05-10 Tim Neumannbackend sampling: support returning post-sampling probs...
2026-05-10 Alessandro... vendor : update cpp-httplib to 0.43.4 (#22888)
2026-05-10 Oliver Walshggml-virtgpu : include missing mutex header (#22810)
2026-05-10 Georgi Gerganovsync : ggml
2026-05-10 Georgi Gerganovggml : bump version to 0.11.1 (ggml/1484)
2026-05-10 scutler-nvinternal AllReduce kernel for CUDA provider (#22299)
2026-05-10 Sigbjørn Skjæretmodel : fix model type check for granite/llama3 and...
2026-05-09 Sumit Chatterjeemodel : add sarvam_moe architecture support (#20275)
2026-05-09 Yuannandevops : updated Nix systems (#22869)
2026-05-09 Davi Henrique... docker : upgraded the default intel compute-runtime...
2026-05-09 Alessandro... cmake : update BoringSSL to 0.20260508.0 (#22839)
2026-05-09 Alexey KopytkoSYCL: reduce allocation overhead during flash attention...
2026-05-09 Devedse[SYCL] Add BF16 support to GET_ROWS operation (#21391)
2026-05-09 Intel AI Get... sycl: Q5_K reorder MMVQ/dequant + Q8_0 reorder MMVQ...
2026-05-09 Intel AI Get... sycl: Battlemage AOT build via spir64_gen + MMQ subgrou...
2026-05-09 AesSedaiAdd flash attention MMA / Tiles to support MiMo-V2...
2026-05-09 Yanzhao Wanghexagon: add HTP kernel for GGML_OP_GATED_DELTA_NET...
2026-05-09 Intel AI Get... sycl: support non-contiguous input in PAD op (#22148)
2026-05-08 Pranav DhinakarFeature hexagon l2 norm (#22816)
2026-05-08 Aldehir Rojascommon : do not wrap raw strings in schema parser for...
2026-05-08 ynankanimodel : support Gemma4_26B_A4B_NVFP4 (#22804)
2026-05-08 Aldehir Rojascommon : revert reasoning budget +inf logit bias (...
2026-05-08 smugman-dotwebui: fix LLM title generation for agentic conversatio...
2026-05-08 Xuan-Son Nguyenserver: support Vertex AI compatible API (#22545)
2026-05-08 Xuan-Son Nguyenserver: (router) expose child model info from router...
2026-05-08 Pascalcuda: fuse snake activation (mul, sin, sqr, mul, add...
2026-05-08 Aleksander... webui: Add Import/Export of Settings configuration...
2026-05-08 Johannes GäßlerCUDA: lower-case PCI bus id, standardize for ggml ...
2026-05-08 miyanvulkan: fix spv shadowing (#22760)
2026-05-08 Max Krasnyanskyggml: update SCHED_DEBUG output to use ggml_op_desc...
2026-05-08 Shawn Guopencl: add q4_0 MoE GEMM for Adreno (#22731)
2026-05-08 Michał Piszczekconvert : fix RuntimeError when stripping FP8 KV-cache...
2026-05-08 Neo Zhangfix script error (#22795sycl : )
2026-05-07 samuraiengmodel: Support sarashina2.2-vision-3b model (#22103)
2026-05-07 leonardHONGCUDA: batch out_prod inner loop with cublasSgemmStrided...
2026-05-07 smugman-dotwebui: add option for LLM title generation (#22265)
2026-05-07 Georgi Gerganovllama : fix device state save/load (#22805)
2026-05-07 shaofeiqiopencl: add opfilter regex for debugging (#22782)
2026-05-07 Aldehir Rojascommon/chat : preserve media markers for typed-content...
2026-05-07 HaoJun ZHANGtests: add long-sequence cases and fix inputs for gated...
2026-05-07 Intel AI Get... sycl: add FILL, CUMSUM, DIAG, SOLVE_TRI, SSM_SCAN,...
2026-05-07 Gaurav GargWrite a readme on Multi-GPU usage in llama.cpp (#22729)
2026-05-07 Georgi Gerganovllama : remove unnecessary seq_id check during state...
2026-05-07 pl752ggml-cpu: Optimized risc-v cpu q1_0 dot
2026-05-07 Pascalmtmd: fix whisper audio tail truncation by exposing...
2026-05-07 AesSedaimodel: Add Mimo v2.5 model support (#22493)
2026-05-07 Pascalwebui: fix ?model= URL param race in router mode (...
2026-05-07 Vishal Singhcodeowners : add ZenDNN backend codeowner (#22772)
2026-05-07 viggywebui: fix flicker issue on dismiss animation on overla...
2026-05-07 Shane Tran... sycl : fix test script (#22737)
2026-05-07 Adrien Gallouëtllama : add missing call to ggml_backend_load_all(...
2026-05-06 tc-mbmtmd : support MiniCPM-V 4.6 (#22529)
2026-05-06 Gilad S.model : don't crash on unsupported architecture (#22742)
2026-05-06 fl0rianrcommon: do not fit to unknown device memory (#22614)
2026-05-06 Georgi Gerganovgguf-py : bump version to 0.19.0 (#22664)
2026-05-06 Yakine Tahtahmtmd: add granite-speech support (ibm-granite/granite...
2026-05-06 David Huggins... feat: migrate to PEP 621 and add uv support (#21907)
2026-05-06 Daniel Beveniusconvert : ignore non-language tensors for Gemma4Model...
2026-05-06 Aleksander... webui: Remove Google Favicons & Improve MCP Information...
2026-05-06 zzzzwcggml-cpu: fuse RMS_NORM + MUL on CPU backend (#22423)
2026-05-06 viggyadd tabindex and aria-hidden (#22699)
2026-05-06 Sigbjørn Skjæretconvert : add filter_tensors method to pre-filter tenso...
2026-05-06 fl0rianrggml : use `CL_DEVICE_GLOBAL_MEM_SIZE` as memory estima...
2026-05-05 Trivikram ReddyHexagon: Process M-tail rows on HMX instead of HVX...
2026-05-05 lhezopencl: refactor Adreno q4_0 (#22335)
2026-05-05 Radoslav Gerganovrpc : use graph uid instead of graph cache (#22701)
2026-05-05 Adrien Gallouëtcommon : fix missing-noreturn warnings when compiling...
2026-05-05 Georgi Gerganovsync : ggml
2026-05-05 Georgi Gerganovggml : bump version to 0.11.0 (ggml/1478)
2026-05-05 Adrien Gallouëtcommon : only load backends when required (#22290)
2026-05-05 Alessandro... vendor : update cpp-httplib to 0.43.3 (#22686)
2026-05-05 Georgi Gerganovserver : validate --tools CLI argument against known...
2026-05-05 Georgi Gerganovllama : add option to save memory in device buffers...
2026-05-05 Sigbjørn Skjæretgraph : handle non-contiguous Q/K/V in mul_mat_aux...
2026-05-05 Ismailggml : implement fast walsh-hadamard transform for...
2026-05-04 Charles Xukleidiai : update to v1.24.0 and use release archive...
2026-05-04 leonardHONGCUDA: use fastdiv for batch index split in get_rows...
2026-05-04 Xuan-Son Nguyenserver: implement /models?reload=1 (#21848)
2026-05-04 Shakhnazar... examples: refactor diffusion generation (#22590)
2026-05-04 JusteLeowebui : fix circular dependency between chat.service...
2026-05-04 Piotr Wilkin... common/autoparser: fixes for newline handling / forced...
2026-05-04 Xuan-Son Nguyenmodel: move `load_hparams` and `load_tensors` to per...
next