Open Hub
Open Hub

 Settings |  Report Duplicate

0
I Use This!
Very High Activity

Commits : Listings

Analyzed about 11 hours ago. based on code collected 1 day ago.
Nov 06, 2025 — Nov 06, 2026
Commit Message Contributor Files Modified Lines Added Lines Removed Code Location Date
opencl: add q6_k multi column tiled GEMV for speculative verification and refactoring (#31758)
Shawn Gu
More... 1 day ago
hexagon: Implement set_tensor_n and improve repacking/tiling robustness (#31744)
Max Krasnyansky
More... 2 days ago
mtmd: enable cmake unity build (#31760)
Xuan-Son Nguyen
More... 2 days ago
tests : drop u8path() (#31755)
Sigbjørn Skjæret
More... 2 days ago
ci: fix build-cmake-pkg ccache (#31705)
Eve
More... 2 days ago
llama: fix kv shifting, add tests, add per-model build_rope (#31683)
Xuan-Son Nguyen
More... 2 days ago
llama, mtmd: (chatterbox) add use_classifier_free_guidance as gguf metadata (#31698)
Xuan-Son Nguyen
More... 2 days ago
models : recursive fix (#31749)
Sigbjørn Skjæret
More... 2 days ago
model : add Ripple (ricursiveai) (#31692)
Nik Bogatyrev
More... 2 days ago
model: Add support for the xing4_0 (#31589)
sxq
More... 2 days ago
ui: prevent a hidden sidebar from intercepting clicks (#31712)
Nick Towle
More... 2 days ago
llama: refactoring: move model to class member of llm_graph_context (#31733)
Xuan-Son Nguyen
More... 2 days ago
server : simplify windows MCP command resolution (#31728)
Adrien Gallouët
More... 2 days ago
vendor : update cpp-httplib to 0.65.0 (#31731)
Adrien Gallouët
More... 2 days ago
ggml-cuda: sanitize post-bias NaNs in MoE selection (#31005)
Zheyuan Chen
More... 2 days ago
vulkan: Implement test-fusion interface (#30769)
Jeff Bolz
More... 2 days ago
CUDA: use highest compiled arch in get_mmvq_mmid_max_batch (#31679)
ManuelPDM
More... 2 days ago
vulkan: RDNA3/4 Large-Tile Split-K Optimization (#30280)
Alex-JP-93
More... 2 days ago
gguf-py : external chat templates have precedence over tokenizer_config (#31717)
Sigbjørn Skjæret
More... 2 days ago
metal : fuse DeepSeek-V4/V4.1 and GLM MoE routing (#31615)
Georgi Gerganov
More... 2 days ago
CUDA/HIP: matrix-core (MFMA) lightning indexer for CDNA2 (gfx90a) (#29050)
Jaden_Mach
More... 2 days ago
CUDA: linearize MoE data layout for MMQ/MMF (#31047)
Johannes Gäßler
More... 2 days ago
vulkan: FWHT kernels for block widths above 512 (#29772)
bri-prism
More... 2 days ago
vulkan : check combined K+V f16 scratch size in FA dequant path (#30487)
Nisbenz
More... 2 days ago
llama-server: Use reference-counted checkpoints instead of deep-copies (#30137)
cwriter
More... 2 days ago
ggml : support `truncate=false` for YaRN (#30206)
Takamichi Ohara
More... 2 days ago
conversion : resolve quantized_layers from source tensor names (#31611)
Daniel Bevenius
More... 3 days ago
metal : use mul_mm for 32 <= K < 64 (#30982)
Hoang Vien Duy
More... 3 days ago
server : reject non-object session updates (#31714)
Adrien Gallouët
More... 3 days ago
fit : account for skipped NextN layers when setting n_gpu_layers (#31569)
Aman Gupta
More... 3 days ago