biondizzle ba67e055f7 Add production FMHA layer comparison test ...

Test loads real model weights, runs attention forward for layers 0-4,
compares production B1 mixed FP8 FMHA output vs PyTorch SDPA reference.
This will reveal the FMHA cosine degradation (was 0.679 at L1) with
real data patterns, not just synthetic random data.

Production values: HD=512, NOPE=448, ROPE=64, H=128, 8 GPUs.

2026-06-03 02:22:23 +00:00

..

e2e

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

e2e_archive

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

integration

Cleanup Step 1: Move root-level files to proper directories

2026-06-02 19:24:39 +00:00

unit

Add production FMHA layer comparison test

2026-06-03 02:22:23 +00:00

check_log.sh

Add check_log.sh convenience script

2026-05-22 17:07:23 +00:00

compare_hf_reference.py

Add HuggingFace reference comparison test

2026-05-31 12:05:19 +00:00

compare_layer0.py

Add HF reference test script

2026-05-31 20:11:37 +00:00

layer_compare.py

Fix remaining mHC API references: layer_compare.py, layer.py comment

2026-05-31 18:38:34 +00:00

requirements.txt

test: add standalone layer 0 comparison test (no vLLM, no Docker)

2026-05-16 02:13:18 +00:00

run_test.sh

run_test.sh: SIGKILL all children of screen session on cleanup

2026-05-22 17:08:12 +00:00

test_minimal_e2e.py

Fix mHCBlock import + relax RoPE round-trip threshold (BF16 noise expected)

2026-05-31 09:17:07 +00:00

test_residual_diagnostic.py

Fix expert weight indexing for 1D tensor

2026-05-31 09:23:10 +00:00

validate_layer.py

Fix dtype mismatch in validate_layer: cast flat to float before F.linear

2026-05-31 20:23:18 +00:00

verify_attention.py

fix verify_attention: proper multi-head SDPA + GQA

2026-05-31 05:55:10 +00:00