nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[bugfix] MiniMax H3: drop the audio/video decode overlap; tests use envs overrides; regenerate env docs

Browse Source
This commit is contained in:
Aryan Kumar
2026-11-01 17:06:18 -08:00
parent 1ee3aff3b6
commit 3a6f4a29b4
9 changed files with 34 additions and 247 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/contributing/env_vars.md
+4 -1
View File
@@ -268,7 +268,7 @@ longer exists also fails the test, so the fixing pull request deletes its entry.
| `FASTVIDEO_H3_FP8_ATTENTION` | bool | `0` | performance | With NVFP4 layer_profile h3_dit_ffn, run MiniMax-H3 attention projections in FP8. |
| `FASTVIDEO_H3_FP8_GRANULARITY` | one of tensor, channel | `tensor` | performance | FP8 scaling granularity for FASTVIDEO_H3_FP8_ATTENTION. |
| `FASTVIDEO_LORA_SIDE_BRANCH` | bool | `0` | performance | Apply inference LoRA adapters as a bf16 side branch next to every target linear instead of merging them, so the adapter strength can change at runtime. Packed NVFP4 or FP8 linears without their original dense weight always use the side branch. |
| `FASTVIDEO_NVFP4_MM_BACKEND` | str | `auto` | performance | FlashInfer mm_fp4 backend for NVFP4 linears, e.g. auto or cutlass. |
| `FASTVIDEO_NVFP4_MM_BACKEND` | str | `auto` | performance | FlashInfer mm_fp4 backend for NVFP4 linears: auto (cudnn for MiniMax-H3 DiT profiles on sm_100), cutlass or cudnn. |
| `FASTVIDEO_NVFP4_MM_ROW_SPLIT` | one of off, table, auto | `off` | performance | Run large cuDNN NVFP4 GEMMs over row chunks where its plan heuristic is slow: off, table (fixed per-shape chunk counts) or auto (time 1/2/4 chunks once per shape; not deterministic across runs). |
| `FASTVIDEO_NVFP4_ACT_AMAX` | path | unset | performance | JSON of calibrated NVFP4 input amax per linear, keyed b<block>.<sub> or full prefix; sets a static activation scale. |
| `FASTVIDEO_NVFP4_DYNAMIC_ACT` | str | `""` | performance | NVFP4 linears that derive the activation scale per call: all, or comma-separated layer-name suffixes such as ff.fc_out. |
@@ -288,6 +288,9 @@ longer exists also fails the test, so the fixing pull request deletes its entry.
| `FASTVIDEO_H3_VAE_INT8_OVERLAY` | bool | `1` | performance | Apply the INT8 ConvRot decoder overlay when the MiniMax-H3 VAE folder ships one; 0 decodes with the dense weights. |
| `FASTVIDEO_H3_VAE_INT8_SHARED_QKV` | bool | `0` | performance | Share the INT8 activation rotation and quantization across the MiniMax-H3 VAE Q/K/V projections. |
| `FASTVIDEO_H3_VAE_INT8_TRANSPOSE_VIEW` | bool | `0` | performance | Use transposed weight views in the MiniMax-H3 VAE INT8 projections. |
| `FASTVIDEO_H3_VAE_COMPILE_BLOCKS` | bool | `0` | performance | Run the MiniMax-H3 video VAE decoder transformer blocks through one regional torch.compile graph: Inductor fuses the fp32 residual scale/add pairs, the RMSNorm+cast and the SwiGLU silu\*mul. |
| `FASTVIDEO_H3_VAE_UINT8_PIXELS` | bool | `1` | performance | Quantize single-GPU MiniMax-H3 video VAE output to uint8 on the GPU per chunk and stream uint8 into the host buffer; frames are bitwise identical to the fp32 path. 0 streams fp32. |
| `FASTVIDEO_H3_VAE_ENCODE_TILE_BATCH` | int | `1` | performance | Spatial tiles per MiniMax-H3 video VAE encoder call (reference and keyframe encodes); 1 encodes per tile. Batched tiles differ from per-tile encoding only in reduction order. |
| `FASTVIDEO_H3_VAE_INT8_FUSED_DEQUANT` | bool | `0` | performance | Fused dequantization epilogue for the MiniMax-H3 VAE INT8 projections. |
| `FASTVIDEO_H3_PINNED_SWAP` | bool | `1` | performance | Swap offloaded MiniMax-H3 modules through exact-size pinned host arenas. |
| `FASTVIDEO_H3_PARK_MODULES` | str | unset | performance | Comma-separated MiniMax-H3 denoise modules parked on the host while the text encoder runs, e.g. vae,audio_vae. |