Skip to content

[WS1][MiniMax-H3] h3_arch_fingerprint, h3_operator_trace, h3_trajectory_artifact: pinned architecture, strict-run ledger and sealed trajectory (RFC #420 stack 1/5) - #567

Open
fusheng-ji wants to merge 8 commits into
RL-Align:test-h3from
fusheng-ji:feat/h3-fingerprint-trace-trajectory
Open

[WS1][MiniMax-H3] h3_arch_fingerprint, h3_operator_trace, h3_trajectory_artifact: pinned architecture, strict-run ledger and sealed trajectory (RFC #420 stack 1/5)#567
fusheng-ji wants to merge 8 commits into
RL-Align:test-h3from
fusheng-ji:feat/h3-fingerprint-trace-trajectory

Conversation

@fusheng-ji

@fusheng-ji fusheng-ji commented Oct 22, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

RFC #420 H3 stack 1/5 (base test-h3, merge in this order): #586 -> #587 -> #588 -> foundation -> projection rows -> WS2 parallel -> token refiner -> full transformer. This PR merges after its parent; until then GitHub also shows the parent's commits. This PR's own diff.

Evidence location: the measurement outputs of this PR (JSON, figures) are not part of its diff. They are on the fork's pr_assets branch under pending/h3-fingerprint-trace-trajectory/ (links in this description are fixed to that commit). Paths such as reports/experiments/... below name where a runner writes its output.

What

  • Architecture fingerprint (rl_engine/models/minimax_h3/fingerprint.py, arch_fingerprint.json, pinned_checkpoint.json): the 33B H3 as a table of
    50 transformer blocks x 17 nodes, 2 token-refiner blocks x 14 nodes, the final norm and 638 tensors (names, shapes, dtypes), pinned to MiniMax-H3@42ed227.
    tools/validation/models/h3_fingerprint.py checks a checkpoint snapshot against it; tools/weights/snapshot_h3_checkpoint.py writes the snapshot.
  • Operator trace ledger (operator_trace.py): every node of a run records which implementation bound it (row, interim, reference, native) and a strict run
    is only accepted when the ledger is complete and every node is row.
  • Trajectory artifact (trajectory.py): a sealed record of a denoising trajectory (per-step velocity / mean, per-modality hashes, optional tensors) with a
    drift_report that names the first step, kind and modality that differ.

Prior art & reuse decision

No existing library offers a pinned per-node architecture table or a ledger of which kernel computed each node: diffusers, vLLM-Omni and SGLang implement the model but
do not expose this; verl, Miles and Vime have no H3 diffusion operators. Nothing to reuse; these are small pure-Python pieces with a CLI each.

Results (H100 / Hopper)

No operator numerics here, so no accuracy/performance charts apply. Measured on NVIDIA H100 (93 GiB, sm90), driver 580.173.02, CUDA 13.0, torch 2.13.0+cu130, pinned MiniMax-H3@42ed227 weights, at head eab901bd.

H100: 77 passed (77 collected) — tests.json.

Results (B200 / Blackwell)

B200: 77 passed (77 collected) — tests.json.

Tests

python -m pytest tests/models/minimax_h3/test_h3_arch_fingerprint.py tests/models/minimax_h3/test_h3_operator_trace.py \
    tests/models/minimax_h3/test_h3_trajectory_artifact.py -q          # 77 passed

black / isort / flake8 clean (pre-commit settings).

Scope / Known limitations

Not part of this PR: video projections (#562), O / gate_up / down GEMMs (#554, #535), full attention (#553), ROCm, SGLang adapter, pipeline parallel. The ledger accepts only row bindings; the interim stand-ins other contributors still own are reported, not hidden.

@coderabbitai

coderabbitai Bot commented Oct 22, 2026 •
edited
Loading

Copy link
Copy Markdown

Important

Review skipped

Too many files!

This PR contains 140 files, which is 40 over the limit of 100.

To get a review, reduce the PR to 100 files or fewer by splitting it into smaller PRs or changing its base branch.

Upgrade to a paid plan to raise the limit.

This review couldn't start because sufficient usage credits or metered capacity aren't available. Add credits or update usage-based reviews in the billing tab, then retry.

Check out review usage here.

Run configuration
Commits

Reviewing files that changed from the base of the PR and between d22d4b4 and 133d250.

Files selected for processing: 140
  • .github/workflows/ci.yml
  • benchmarks/models/benchmark_h3_conditioning.py
  • build_tools/extensions.py
  • csrc/bindings/ops.cpp
  • csrc/cuda/h3/adaln_row_gather.cu
  • csrc/cuda/h3/det_linear.cu
  • csrc/cuda/h3/gate_residual.cu
  • csrc/cuda/h3/rmsnorm_modulate.cu
  • csrc/cuda/h3/timestep_sinusoid.cu
  • docs/.nav.yml
  • docs/operators/README.md
  • docs/operators/h3-adaln-gate-residual.md
  • docs/operators/h3-adaln-projection.md
  • docs/operators/h3-adaln-row-gather.md
  • docs/operators/h3-arch-fingerprint.md
  • docs/operators/h3-final-adaln-out.md
  • docs/operators/h3-one-block.md
  • docs/operators/h3-operator-trace.md
  • docs/operators/h3-rmsnorm.md
  • docs/operators/h3-sp-norm-adaln.md
  • docs/operators/h3-timestep-mlp.md
  • docs/operators/h3-timestep-sinusoid.md
  • docs/operators/h3-tp-adaln-3mod.md
  • docs/operators/h3-trajectory-artifact.md
  • examples/models/minimax_h3/README.md
  • examples/models/minimax_h3/candidate.sbatch
  • examples/models/minimax_h3/diagnose-block.sbatch
  • examples/models/minimax_h3/full-model-ensemble-rule.json
  • examples/models/minimax_h3/full-model-thresholds.json
  • examples/models/minimax_h3/generation-compare.sbatch
  • examples/models/minimax_h3/generation-contract.json
  • examples/models/minimax_h3/generation-inputs.json
  • examples/models/minimax_h3/generation-prompt.txt
  • examples/models/minimax_h3/generation-resume-check.sbatch
  • examples/models/minimax_h3/generation.sbatch
  • examples/models/minimax_h3/reference-manifest.json
  • examples/models/minimax_h3/reference.sbatch
  • rl_engine/_C.pyi
  • rl_engine/backends/cuda/model_specific/__init__.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/__init__.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/adaln_modulation.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/adaln_projection.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/adaln_row_gather.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/det_linear.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/final_adaln_out.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/gate_residual.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/rmsnorm.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/sp_norm_adaln.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/timestep_mlp.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/timestep_sinusoid.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/tp_adaln_projection.py
  • rl_engine/backends/cuda/model_specific/minimax_h3/ws2_comm.py
  • rl_engine/models/minimax_h3/arch_fingerprint.json
  • rl_engine/models/minimax_h3/fingerprint.py
  • rl_engine/models/minimax_h3/operator_trace.py
  • rl_engine/models/minimax_h3/pinned_checkpoint.json
  • rl_engine/models/minimax_h3/trajectory.py
  • rl_engine/reference/minimax_h3/__init__.py
  • rl_engine/reference/minimax_h3/adaln_projection.py
  • rl_engine/reference/minimax_h3/adaln_row_gather.py
  • rl_engine/reference/minimax_h3/block.py
  • rl_engine/reference/minimax_h3/final_adaln_out.py
  • rl_engine/reference/minimax_h3/fixed_order.py
  • rl_engine/reference/minimax_h3/gate_residual.py
  • rl_engine/reference/minimax_h3/rmsnorm.py
  • rl_engine/reference/minimax_h3/timestep_mlp.py
  • rl_engine/reference/minimax_h3/timestep_sinusoid.py
  • rl_engine/runtime/registry.py
  • rl_engine/validation/models/h3_block.py
  • rl_engine/validation/models/h3_cases.py
  • rl_engine/validation/models/h3_chain.py
  • rl_engine/validation/models/h3_full_manifest.json
  • rl_engine/validation/models/h3_full_model.py
  • rl_engine/validation/models/h3_generation_resume.py
  • rl_engine/validation/models/h3_manifest.json
  • rl_engine/validation/models/h3_provider.py
  • rl_engine/validation/models/h3_report.py
  • rl_engine/validation/models/h3_weights.py
  • rl_engine/validation/models/h3_ws2.py
  • rl_engine/validation/operators/operator_inputs.py
  • rl_engine/validation/operators/operator_specs.py
  • tests/build/test_build_platform_collectives.py
  • tests/models/minimax_h3/conftest.py
  • tests/models/minimax_h3/test_h3_adaln_gate_residual.py
  • tests/models/minimax_h3/test_h3_adaln_modulation.py
  • tests/models/minimax_h3/test_h3_adaln_projection.py
  • tests/models/minimax_h3/test_h3_adaln_row_gather.py
  • tests/models/minimax_h3/test_h3_arch_fingerprint.py
  • tests/models/minimax_h3/test_h3_benchmark_timing.py
  • tests/models/minimax_h3/test_h3_chain_replay_cli.py
  • tests/models/minimax_h3/test_h3_cli.py
  • tests/models/minimax_h3/test_h3_conditioning_e2e.py
  • tests/models/minimax_h3/test_h3_det_linear.py
  • tests/models/minimax_h3/test_h3_final_adaln_out.py
  • tests/models/minimax_h3/test_h3_full_model.py
  • tests/models/minimax_h3/test_h3_generation_resume.py
  • tests/models/minimax_h3/test_h3_native_validation.py
  • tests/models/minimax_h3/test_h3_one_block.py
  • tests/models/minimax_h3/test_h3_operator_trace.py
  • tests/models/minimax_h3/test_h3_report.py
  • tests/models/minimax_h3/test_h3_rmsnorm.py
  • tests/models/minimax_h3/test_h3_sp_norm_adaln.py
  • tests/models/minimax_h3/test_h3_timestep_mlp.py
  • tests/models/minimax_h3/test_h3_timestep_sinusoid.py
  • tests/models/minimax_h3/test_h3_tp_adaln.py
  • tests/models/minimax_h3/test_h3_trajectory_artifact.py
  • tests/models/minimax_h3/test_h3_weights.py
  • tests/models/minimax_h3/test_h3_ws2_processes.py
  • tests/models/minimax_h3/test_prepare_h3_weights.py
  • tests/runtime/test_dispatch.py
  • tests/validation/operators/test_ws1_gtest_gpu.py
  • tools/migration/README.md
  • tools/migration/layout.json
  • tools/validation/models/h3_bitwise_reuse.py
  • tools/validation/models/h3_block_diagnostic.py
  • tools/validation/models/h3_block_replay.py
  • tools/validation/models/h3_block_ulp_sweep.py
  • tools/validation/models/h3_candidate_prepare.py
  • tools/validation/models/h3_chain_replay.py
  • tools/validation/models/h3_evidence.py
  • tools/validation/models/h3_evidence_integrity.py
  • tools/validation/models/h3_fingerprint.py
  • tools/validation/models/h3_first_step_diagnostic.py
  • tools/validation/models/h3_full_compare.py
  • tools/validation/models/h3_full_ensemble_rule.py
  • tools/validation/models/h3_full_generation.py
  • tools/validation/models/h3_full_model.py
  • tools/validation/models/h3_full_provider_spread.py
  • tools/validation/models/h3_generation_adopt.py
  • tools/validation/models/h3_generation_compare.py
  • tools/validation/models/h3_operator_trace.py
  • tools/validation/models/h3_prior_art.py
  • tools/validation/models/h3_trajectory.py
  • tools/validation/models/h3_ws2_evidence.py
  • tools/validation/models/plot_h3_bitwise_reuse.py
  • tools/validation/models/plot_h3_block.py
  • tools/validation/models/plot_h3_evidence.py
  • tools/validation/models/plot_h3_prior_art.py
  • tools/weights/prepare_h3_weights.py
  • tools/weights/snapshot_h3_checkpoint.py

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Comment @coderabbitai help to get the list of available commands.

This was referenced Oct 22, 2026
Open
Open
Open
@fusheng-ji
feat(h3): add architecture fingerprint (h3_arch_fingerprint)
b3c6b81 
Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
(cherry picked from commit eaba5efe3df971ea9d1a969f53e48f09e09ed176)
Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
(cherry picked from commit 7da0574)
@fusheng-ji
feat(h3): add operator trace ledger (h3_operator_trace)
a4b9812 
Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
(cherry picked from commit b45190d08fc033c7e63ad821d3918eb32dd454f6)
Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
(cherry picked from commit b5536d6)
@fusheng-ji
feat(h3): add sealed trajectory artifact (h3_trajectory_artifact)
57e0169 
Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
(cherry picked from commit ad1925045b522772bf56f8468b23cca47f04156b)
Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
(cherry picked from commit f9041e8)
@fusheng-ji
style(h3): black/isort/flake8 for the foundation rows
dc36d1d 
Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
(cherry picked from commit b44540e)
@fusheng-ji
[WS1][CUDA][MiniMax-H3] ws1_one_h3_block + full-model qualification: …
17d0e9e 
…block 0 node-by-node and 50-block/generation gates

Squashes the one-block branch (its row-by-row history: timestep sinusoid, RMSNorm, AdaLN rows,
sequence/tensor parallel norm rows, final AdaLN, one block, 50-block qualification) onto the current
test-h3 so the pull request carries a reviewable, signed history. RFC RL-Align#420.

Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
@fusheng-ji
fix(h3): type the trajectory step body so mypy accepts StepRecord(**b…
eab901b 
…ody)

Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
@fusheng-ji
fusheng-ji force-pushed the feat/h3-fingerprint-trace-trajectory branch from b44540e to eab901b Compare October 22, 2026 21:04
fusheng-ji added a commit to fusheng-ji/RL-Kernel that referenced this pull request Oct 23, 2026
@fusheng-ji
evidence(h3 follow-ups): B200 results for the stack heads of RL-Align…
a27b08d 
…#567 RL-Align#568 RL-Align#570 RL-Align#571 RL-Align#574 RL-Align#575

Test summaries (tests.json), runner outputs and figures measured on NVIDIA B200 (sm100),
driver 580, CUDA 13.0, torch 2.13.0+cu130, MiniMax-H3@42ed227, clean trees at the PR heads
eab901b, 3cf51bf, 6de320d, eb7840b, af3dcae and 4f7c5d1. Figures use B200 axis labels.
No host names, paths or scheduler identifiers.

Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
fusheng-ji added a commit to fusheng-ji/RL-Kernel that referenced this pull request Oct 23, 2026
@fusheng-ji
evidence(R2): H100 RL-Align#567 tests, H100 integration env, dual-tra…
180cccd 
…jectory diag summary

- h3-fingerprint-trace-trajectory-h100/tests.json (77 passed, eab901b)
- environment.json for RL-Align#574/RL-Align#575 H100 adapter reproducibility pins
- dual_trajectory_diag_summary.json (H100/B200 diag strict 0/16 on seeds 11/22/33)

Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
@Flink-ddd Flink-ddd added platform: cuda Specific optimizations or bugs in NVIDIA graphics cards (such as FlashInfer, TMA optimizations) new-model MiniMax-H3 WS1 labels Oct 23, 2026
This was referenced Oct 25, 2026
Draft
Closed
@fusheng-ji
Merge test-h3 into feat/h3-one-block
0da990e 
Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>
@fusheng-ji
Merge local/h3merge/h3-one-block into feat/h3-fingerprint-trace-traje…
133d250 
…ctory

Signed-off-by: Wenbo Ji <36562829+fusheng-ji@users.noreply.github.com>

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@Flink-ddd Flink-ddd Awaiting requested review from Flink-ddd Flink-ddd is a code owner
@inaniloquentee inaniloquentee Awaiting requested review from inaniloquentee inaniloquentee is a code owner
@bitborne bitborne Awaiting requested review from bitborne bitborne is a code owner
@KJLdefeated KJLdefeated Awaiting requested review from KJLdefeated KJLdefeated is a code owner
@ryankert01 ryankert01 Awaiting requested review from ryankert01 ryankert01 is a code owner

Assignees

No one assigned

Labels

MiniMax-H3 new-model platform: cuda Specific optimizations or bugs in NVIDIA graphics cards (such as FlashInfer, TMA optimizations) WS1

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@fusheng-ji @Flink-ddd