psv666andClaude Opus 5 009b80d686 [Bugfix][MiniCPM-o] Wire the duplex sampling hook into the NPU AR model runner (#5895) ...

Signed-off-by: psv666 <2693925048@qq.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>

2026-08-07 22:38:45 +08:00

..

test_capture_replay_contract.py

[Refactor][WIP] Add missing test for modelrunner (G1/N) (#5333)

2026-07-27 16:24:47 +08:00

test_fa3_scheduler_metadata_size.py

[Refactor][WIP] Add missing test for modelrunner (G1/N) (#5333)

2026-07-27 16:24:47 +08:00

test_gpu_ar_model_runner.py

[Refactor][WIP] Add missing test for modelrunner (G1/N) (#5333)

2026-07-27 16:24:47 +08:00

test_gpu_generation_model_runner.py

[Bugfix] Skip non-positive scheduled token spans in omni stage runners (#5269)

2026-07-22 16:01:45 +00:00

test_memory_utils.py

[Refactor][WIP] Add missing test for modelrunner (G1/N) (#5333)

2026-07-27 16:24:47 +08:00

test_min_tokens_stop_ids_guard.py

[Bugfix] Drop out-of-vocabulary stop ids from min-tokens masking (qwen3-tts min_tokens engine crash) (#4971)

2026-07-08 11:24:31 -07:00

test_native_duplex_hooks.py

[Bugfix][MiniCPM-o] Wire the duplex sampling hook into the NPU AR model runner (#5895)

2026-08-07 22:38:45 +08:00

test_omni_connector_mixin.py

[Core] Cleanup Omni connector runtime and transfer backends (#5096)

2026-07-22 09:44:15 +08:00

test_omni_gpu_model_runner.py

[perf] Minicpm o4.5 optimization (#5228)

2026-07-24 17:20:39 +08:00

test_payload_span.py

[Refactor][WIP] Add missing test for modelrunner (G1/N) (#5333)

2026-07-27 16:24:47 +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

test_sampler_history_backfill.py

[Refactor][WIP] Add missing test for modelrunner (G1/N) (#5333)

2026-07-27 16:24:47 +08:00

test_worker_base.py

[Refactor][WIP] Add missing test for modelrunner (G1/N) (#5333)

2026-07-27 16:24:47 +08:00