Skip to content

Actions: hao-ai-lab/FastVideo

Actions

Welcome First-Time Contributors

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
community-welcome.yml
633 workflow runs
633 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[bugfix] Write generated documentation as UTF-8 Welcome First-Time Contributors #608: Pull request #1797 opened by shahradzomorrodi
39s
39s
[feat] add MXFP8 support on H3 Welcome First-Time Contributors #607: Pull request #1796 opened by Davids048
30s
30s
[feat]: add opt-in CUDA TAEH3 preview decode for FastH3 Welcome First-Time Contributors #606: Pull request #1795 opened by aryan5v
25s
25s
[feat] Add an optional MLX TAEH3 preview decoder Welcome First-Time Contributors #605: Pull request #1794 opened by aryan5v
23s
23s
[perf] Sequential MiniMax H3 start with GPU-direct DiT load Welcome First-Time Contributors #604: Pull request #1793 opened by aryan5v
26s
26s
[perf] Speed up exact MiniMax H3 MLX inference Welcome First-Time Contributors #603: Pull request #1792 opened by aryan5v
28s
28s
[bugfix] encoders: keep Qwen2.5-VL importable on transformers 5 Welcome First-Time Contributors #602: Pull request #1791 opened by alanhuangyoo
21s
21s
[docs]: Cookbook catalog improvements Welcome First-Time Contributors #601: Pull request #1790 opened by aryan5v
22s
22s
[feat] Add MiniMax H3 MLX spatial fast mode Welcome First-Time Contributors #600: Pull request #1789 opened by SuhaanCoding
20s
20s
[perf]: dispatch wide-M affine H3 MLX linears through dequant plus dense GEMM Welcome First-Time Contributors #599: Pull request #1788 opened by aryan5v
27s
27s
[docs] Add model-family inference cookbook Welcome First-Time Contributors #598: Pull request #1787 opened by aryan5v
22s
22s
[bugfix] Shut down Inductor workers gracefully Welcome First-Time Contributors #597: Pull request #1786 opened by Satyam-53
24s
24s
[misc]: surface GenerationResult.peak_memory_mb in the MiniMax H3 examples Welcome First-Time Contributors #596: Pull request #1785 opened by KyleNeverGivesUp
20s
20s
[feat] Add streaming and GPU-accelerated LoRA extraction Welcome First-Time Contributors #595: Pull request #1784 opened by shaoxiongduan
22s
22s
[misc] FastVideo Studio UI Additions (H3 Ref2V support) Welcome First-Time Contributors #594: Pull request #1783 opened by kevin314
27s
27s
[bugfix] Harden OpenAI serving after post-merge review Welcome First-Time Contributors #593: Pull request #1782 opened by SolitaryThinker
43s
43s
[feat] Align multimodal OpenAI serving APIs Welcome First-Time Contributors #592: Pull request #1781 opened by SolitaryThinker
37s
37s
[bugfix]: apply FP8 to MiniMax H3's feed-forward Welcome First-Time Contributors #591: Pull request #1780 opened by KyleNeverGivesUp
21s
21s
[feat] Add streaming MiniMax-H3 LoRA extractor Welcome First-Time Contributors #590: Pull request #1779 opened by shaoxiongduan
36s
36s
[chore]: release v0.2.1 Welcome First-Time Contributors #589: Pull request #1778 opened by SolitaryThinker
18s
18s
[misc] pin fastvideo-kernel to exact 0.3.5 Welcome First-Time Contributors #588: Pull request #1777 opened by SolitaryThinker
21s
21s
[perf] Add MiniMax H3 MLX VSA and SIMD attention Welcome First-Time Contributors #587: Pull request #1776 opened by aryan5v
19s
19s
[chore] release fastvideo-kernel 0.3.5 Welcome First-Time Contributors #586: Pull request #1775 opened by SolitaryThinker
27s
27s
[bugfix]: pin fastvideo-kernel to Torch 2.12.0 Welcome First-Time Contributors #585: Pull request #1774 opened by SolitaryThinker
24s
24s
[feat]: Add Cosmos Predict (Cosmos 2.5) Model Port and Staged Pipeline Welcome First-Time Contributors #584: Pull request #1773 opened by techverve
24s
24s