roikoren755 737bfa3a43 [Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233) ...

Signed-off-by: Roi Koren <roik@nvidia.com>

2026-05-18 14:54:00 +03:00

..

__init__.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test_async_scheduling.py

[CI] Fix test_async_scheduling.py flakiness (#42455)

2026-05-12 21:38:32 +00:00

test_cascade_attention.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test_context_length.py

[BugFix] --max-model-len=-1 causes over-limit requests to hang and starve the entire service (#39102)

2026-04-08 14:03:17 -07:00

test_correctness_sliding_window.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test_kv_sharing_fast_prefill.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test_mamba_prefix_cache.py

[Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233)

2026-05-18 14:54:00 +03:00

test_min_tokens.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test_pooling_chunked_prefill.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test_streaming_input.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00