daniel/h3-blackwell-runtime
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
Direct MiniMax H3 CUDA runtime
71 commits 3 branches 0 tags 34 MiB
Find a file
Daniel Maddern 9c9e0857c2 Load direct VAE weights as float32
2026-08-14 00:52:57 +07:00
benchmarks Initial direct H3 runtime 2026-08-12 14:12:42 +07:00
src/h3_blackwell_runtime Load direct VAE weights as float32 2026-08-14 00:52:57 +07:00
tools Compare VAE decoder projection output 2026-08-14 00:34:36 +07:00
wheels Cache GB10 SageAttention3 wheel 2026-08-12 15:21:03 +07:00
.gitignore Initial direct H3 runtime 2026-08-12 14:12:42 +07:00
compose.spark-comfy-lab.yml Initial direct H3 runtime 2026-08-12 14:12:42 +07:00
compose.spark.yml Mount documented H3 artifacts on Spark 2026-08-13 14:44:43 +07:00
Dockerfile.spark Add fastsafetensors loader option 2026-08-13 23:35:01 +07:00
PARITY.md Record sampler wrapper boundary fix 2026-08-13 16:57:44 +07:00
PLAN.md Initial direct H3 runtime 2026-08-12 14:12:42 +07:00
pyproject.toml Add fastsafetensors loader option 2026-08-13 23:35:01 +07:00
README.md Add H3 parity diagnostics 2026-08-12 21:11:02 +07:00

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:

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:

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:

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.