h3-blackwell-runtime/README.md
2026-08-20 22:08:52 +07:00

117 lines
7.3 KiB
Markdown

# H3 Blackwell Runtime
Direct MiniMax H3 Ref2VA runtime research project. ComfyUI is the checkpoint and correctness oracle, not the target runtime.
See [`H3_PROMPT_GUIDE.md`](H3_PROMPT_GUIDE.md) for the project's H3 audiovisual
prompt structure, dialogue syntax, lip-sync controls, soundscape rules, tested
failure modes, and reusable templates.
## First Gate
Inspect the mounted H3 NVFP4 safetensors headers before designing an importer:
```powershell
python .\tools\inspect_safetensors.py /runpod-volume/ComfyUI/models/diffusion_models/minimax_h3_ref2va_pruned_nvfp4.safetensors
```
Write the output to `artifacts/checkpoints/` on the mounted volume. The result must identify packed weights, scales, and tensor naming before any kernel conversion work begins.
## Benchmark Contract
`benchmarks/ref2va-960x544-124f.json` is the single-GPU performance contract. Record direct-runner results as JSON and compare them with:
```powershell
python .\tools\compare_benchmark.py --result direct-result.json
```
## DGX Spark
`Dockerfile.spark` and `compose.spark.yml` prepare an ARM64 GB10 development image using the existing AEON CUDA 13/SageAttention3 base. The compose target opens a shell only; it does not start inference.
### Forgejo Pulls From Spark
The Spark checkout uses Forgejo through the host's published local SSH port and a dedicated key:
```bash
cd /home/daniel/aeon-spark-test/h3/h3-blackwell-runtime
git config core.sshCommand 'ssh -i ~/.ssh/id_ed25519_forgejo_h3 -o IdentitiesOnly=yes'
git remote set-url origin ssh://git@127.0.0.1:2222/daniel/h3-blackwell-runtime.git
git pull --ff-only origin master
```
The private key remains on Spark at `~/.ssh/id_ed25519_forgejo_h3`; only its public key is registered in Forgejo.
## Runtime Output
Generation and latent-decode tools are quiet by default: they suppress ffmpeg banners and only print compact JSON summaries. Use these flags when debugging:
- `--progress`: print per-step sampler timing in `tools/direct_t2v_preview.py`.
- `--profile-memory`: print memory checkpoints in `tools/direct_t2v_preview.py`.
- `--ffmpeg-loglevel info`: show ffmpeg details instead of the default `error` level.
- `--quiet`: suppress JSON summary lines.
- `--vae-dtype float16`: use Comfy-style FP16 video VAE decode in `tools/direct_t2v_preview.py` or `tools/decode_video_latent.py`; this is the default runtime path. Use `--vae-dtype float32` only for exact direct-path diagnostics. `tools/direct_t2v_preview.py` also accepts `H3_VAE_DTYPE`.
- `--vae-tile-size 256`: set the direct video VAE spatial tile size. `tools/direct_t2v_preview.py` also accepts `H3_VAE_TILE_SIZE`.
Standalone `tools/compare_*`, `tools/trace_*`, `tools/inspect_*`, and `tools/patch_comfy_*` scripts are debugging utilities and remain opt-in by being separate commands.
## Hot Runtime Service
`tools/serve_hot_runtime.py` keeps Qwen, H3, video VAE, and audio VAE resident in one process. Start the optional Spark service with:
```bash
docker compose -f compose.spark.yml up -d h3-hot-runtime
```
Use `GET /ready` to confirm resident model readiness. Use `POST /generate` with JSON fields like `prompt`, `output`, `width`, `height`, `frames`, `steps`, `seed`, and optional `attention`. Supported request-level attention values are reported by `/ready`; switching attention does not reload model weights. The hot image includes Sage2, forced cuDNN SDPA, and Comfy Kitchen INT8 attention. Sage2 is the default based on the 960x544x124 GB10 benchmark and the existing parity baseline.
Set `"upscale": 2.0` to apply the resident H3-native learned latent upscaler
between sampling and VAE decode in the same request. `width` and `height` remain
the low-resolution sampling canvas; the response reports both source and final
dimensions. Video is upscaled before decoding, while H3's jointly generated
audio latent follows the normal decode and mux path unchanged. Omit `upscale`,
set it to `null`, or set it to `1` to disable this stage.
Successful requests retain only the final MP4 by default. `save_latent` is
opt-in. Set `"keep_intermediates": true` only for diagnostics that require the
separate WAV and video-only MP4; otherwise both are removed after muxing.
The Spark hot service also keeps the official FL2VA Turbo adapters resident. Set `turbo` to `"4step"` for v1.1 768p (shift 6/3) or `"8step"` for v1.0 (shift 12/3). The matching step count is selected by default and enforced when `steps` is supplied. Set `turbo` to `null` or `"none"` for the base beta/RES path. Turbo uses its separate uniform training-Euler schedule and cannot be combined with denoiser caching.
See [`TURBO.md`](TURBO.md) for artifact hashes, implementation details, API examples, validation evidence, and matched GB10 performance results.
The optional H3-native learned 3D upscaler operates directly on latents saved by
the hot runtime. See [`H3_LATENT_UPSCALER.md`](H3_LATENT_UPSCALER.md) for the
pinned checkpoint, standalone command, GB10 benchmark, proof paths, and current
quality limitations.
Exact memory/lifetime options:
- `attention: "kj_head_sliced"` slices attention heads and runs the slice backend from `H3_HEAD_SLICE_BACKEND` (`sage2` by default) with `H3_HEAD_SLICE_SIZE` heads per slice (`8` by default).
- `attention: "cudnn_sdpa"` forces cuDNN SDPA with no fallback to another PyTorch kernel.
- `attention: "ck_int8"` uses Comfy Kitchen's approximate INT8 Q/K/V attention kernel.
- `attention: "flash4"` uses the pinned official FlashAttention-4 CuTeDSL
Blackwell kernel with strict validation and no fallback. See
[`FLASH4.md`](FLASH4.md) for versions, numerical validation, limitations, and
the matched GB10 benchmark.
- `attention: "sol_attn"` routes eligible H3 attention calls through the pinned ComfyUI Sol-Attn Triton kernel vendored into the Spark image. Configure with `H3_SOL_TAU` (`1.3`), `H3_SOL_MIN_TOKENS` (`4096`), `H3_SOL_THRESH_TYPE` (`diag`), `H3_SOL_INT8_QK`, `H3_SOL_INT8_PV`, `H3_SOL_FALLBACK` (`sage2`), and `H3_SOL_STRICT`.
- `--mlp-chunks N` on `tools/serve_hot_runtime.py` or `tools/direct_t2v_preview.py` chunks H3 SwiGLU rows exactly to reduce peak activation memory. Default is `1` (disabled).
Approximate cache options are opt-in and must be quality-gated per prompt:
- `cache_mode: "easycache"` reuses cached denoised deltas while cumulative latent input change stays below `cache_threshold`.
- `cache_mode: "h3_cache"` reuses cached denoised deltas when the current per-step latent input change is below `cache_threshold`.
- Both modes accept `cache_start_percent`, `cache_end_percent`, and `cache_subsample_factor` in `POST /generate`; the CLI exposes equivalent `--cache-*` flags.
## Project TODO
- [ ] Develop an H3-specific attention backend optimized for the model's actual
GB10 tensor shapes. Validate numerical behavior and subjective output quality
against SDPA, then benchmark it with the existing two-person dialogue matrix.
- [ ] Isolate and fix the H3 startup audio artifact in the latent/AudioVAE path.
The artifact reproduced across every attention and Turbo test in the current
two-person dialogue matrix, and matched direct-runtime and Comfy SDPA outputs
have effectively identical audio. Capture affected audio latents and lossless
pre-AAC PCM, separate first-latent generation from AudioVAE boundary behavior,
and build a selective model-path fix. Do not use unconditional output trimming
or fading because valid audio can begin immediately, as demonstrated by the
nightclub music-onset test.