h3-blackwell-runtime/README.md

# H3 Blackwell Runtime

Direct MiniMax H3 Ref2VA runtime research project. ComfyUI is the checkpoint and correctness oracle, not the target runtime.

## 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.

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: "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.