Aryan KumarandAryan Kumar ac81198d33 [new-model] Open-H3-Regenerate-2K: 768P H3 draft to 2560x1440, served on the OpenAI video routes (#2035) ...

Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>

2026-11-01 22:45:09 -08:00

..

test_linear_mlp_quant_gating.py

[refactor]: linear/mlp FP4 path additions for Wan-2.1 (Attn-QAT 6/12) (#1390)

2026-06-08 14:51:57 -07:00

test_lora_merge_precision.py

[new-model] Open-H3-Regenerate-2K: 768P H3 draft to 2560x1440, served on the OpenAI video routes (#2035)

2026-11-01 22:45:09 -08:00

test_lora_side_branch.py

[bugfix]: compile only the LoRA delta, not the wrapped base layer

2026-10-28 14:49:15 -07:00

test_mxfp8_optional_quack.py

[bugfix] FA4 JIT cache vs tuning env, MXFP8 import and scale dtype, H3 VSA gate double quantization (#2049)

2026-11-01 19:11:25 -08:00

test_mxfp8_scaled_mm_scale_dtype.py

[bugfix] FA4 JIT cache vs tuning env, MXFP8 import and scale dtype, H3 VSA gate double quantization (#2049)

2026-11-01 19:11:25 -08:00

test_nvfp4_mm_backend.py

[perf] MiniMax H3: faster FP4 attention padding, uint8 VAE pixel path and cuDNN FP4 GEMMs (#2046)

2026-11-01 22:23:10 -08:00

test_pdd_linear.py

[feat] FastH3 Ref2VA PDD inference with reference-video VSA sparsity (#1907)

2026-10-02 11:28:07 -07:00

test_rmsnorm_forward_dispatch.py

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

test_triton_fused_norm.py

[bugfix] Repair DreamVerse and failing CI gates (#1958)

2026-10-16 17:15:38 -07:00