Skip to content

Actions: hao-ai-lab/FastVideo

Actions

Slash Commands

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
ci-slash-commands.yml
2,408 workflow runs
2,408 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
[feat] add MXFP8 support on H3 Slash Commands #2333: Issue comment #1796 (comment) created by mergify Bot
7s
7s
[feat]: add opt-in CUDA TAEH3 preview decode for FastH3 Slash Commands #2332: Issue comment #1795 (comment) created by mergify Bot
2s
2s
[perf]: MiniMax H3 on GB10 - load pipeline components on demand instead of all at once Slash Commands #2331: Issue comment #1761 (comment) created by aryan5v
1s
1s
[perf]: MiniMax H3 on GB10 - load pipeline components on demand instead of all at once Slash Commands #2330: Issue comment #1761 (comment) created by mergify Bot
8s
8s
[bugfix]: workers killed by a signal now log the reason Slash Commands #2329: Issue comment #1725 (comment) created by mergify Bot
1s
1s
[feat] Add Ring Attention support Slash Commands #2328: Issue comment #1694 (comment) created by Davids048
1s
1s
[feat] Add an optional MLX TAEH3 preview decoder Slash Commands #2327: Issue comment #1794 (comment) created by mergify Bot
1s
1s
[perf] Sequential MiniMax H3 start with GPU-direct DiT load Slash Commands #2326: Issue comment #1793 (comment) created by mergify Bot
7s
7s
[perf] Speed up exact MiniMax H3 MLX inference Slash Commands #2325: Issue comment #1792 (comment) created by mergify Bot
1s
1s
[bugfix] encoders: keep Qwen2.5-VL importable on transformers 5 Slash Commands #2324: Issue comment #1791 (comment) created by mergify Bot
1s
1s
[docs]: Cookbook catalog improvements Slash Commands #2323: Issue comment #1790 (comment) created by mergify Bot
1s
1s
[docs]: Cookbook catalog improvements Slash Commands #2322: Issue comment #1790 (comment) created by mergify Bot
8s
8s
[feat] Add MiniMax H3 MLX spatial fast mode Slash Commands #2321: Issue comment #1789 (comment) created by aryan5v
10s
10s
[feat] Add MiniMax H3 MLX spatial fast mode Slash Commands #2320: Issue comment #1789 (comment) created by mergify Bot
1s
1s
[perf]: dispatch wide-M affine H3 MLX linears through dequant plus dense GEMM Slash Commands #2319: Issue comment #1788 (comment) created by aryan5v
7s
7s
[perf]: dispatch wide-M affine H3 MLX linears through dequant plus dense GEMM Slash Commands #2318: Issue comment #1788 (comment) created by mergify Bot
1s
1s
[perf]: dispatch wide-M affine H3 MLX linears through dequant plus dense GEMM Slash Commands #2317: Issue comment #1788 (comment) created by mergify Bot
1s
1s
[docs] Add model-family inference cookbook Slash Commands #2316: Issue comment #1787 (comment) created by mergify Bot
7s
7s
Slash Commands Slash Commands #2315: created by FlappyBob
1s
1s
[bugfix] Shut down Inductor workers gracefully Slash Commands #2314: Issue comment #1786 (comment) created by mergify Bot
2s
2s
[misc]: surface GenerationResult.peak_memory_mb in the MiniMax H3 examples Slash Commands #2313: Issue comment #1785 (comment) created by mergify Bot
1s
1s
[feat] Add streaming and GPU-accelerated LoRA extraction Slash Commands #2312: Issue comment #1784 (comment) created by mergify Bot
1s
1s
[feat]: add MiniMax H3 Ref2VA and LoRA training support Slash Commands #2311: Issue comment #1757 (comment) created by Yanghao-Wang
1s
1s
[feat]: add MiniMax H3 Ref2VA and LoRA training support Slash Commands #2310: Issue comment #1757 (comment) created by Yanghao-Wang
11s
11s
[misc] FastVideo Studio UI Additions (H3 Ref2V support) Slash Commands #2309: Issue comment #1783 (comment) created by mergify Bot
1s
1s