amy-why-3459 9ceca4ec85 [Bugfix] Fix full-payload mm splitting for dual hidden/scheduled batch axes (#4870 follow-up) (#4910) ...

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>

2026-07-06 15:08:05 +08:00

..

test_gpu_ar_model_runner.py

[Bugfix] Fix full-payload mm splitting for dual hidden/scheduled batch axes (#4870 follow-up) (#4910)

2026-07-06 15:08:05 +08:00

test_gpu_generation_model_runner.py

[Core] Performance fix for orchestrator bottleneck: separates inter-stage from client outputs (#4527)

2026-06-29 17:43:36 +02:00

test_omni_connector_mixin.py

[Refactor] msgspec standardisation for data entry key names and improved type checks (#3149)

2026-05-12 14:30:13 +08:00

test_omni_gpu_model_runner.py

[Bugfix][Qwen3-TTS] Keep seeded residual MTP sampling batched (#4889)

2026-07-05 21:47:06 +08:00

test_process_gpu_memory.py

[Refactor] Replace and ban a few torch.cuda functions in favor of torch.accelerator replacements. (#3365)

2026-05-07 23:23:59 +08:00