Matthew Bonanni 268bed9cf3 [Bugfix][Async] Fix async spec decoding with hybrid models (#38556) ...

Signed-off-by: SandishKumarHN <sandishkumarhn@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: SandishKumarHN <sandishkumarhn@gmail.com>
(cherry picked from commit 757068dc65)

2026-04-01 01:02:35 -07:00

..

__init__.py

…

test_acceptance_length.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

test_backup_token_async_spec.py

[Bugfix][Async] Fix async spec decoding with hybrid models (#38556)

2026-04-01 01:02:35 -07:00

test_eagle_step_kernel.py

…

test_eagle.py

[Bugfix][Async] Fix async spec decoding with hybrid models (#38556)

2026-04-01 01:02:35 -07:00

test_extract_hidden_states.py

[Bugfix][Async] Fix async spec decoding with hybrid models (#38556)

2026-04-01 01:02:35 -07:00

test_max_len.py

…

test_mtp.py

…

test_ngram.py

…

test_speculators_eagle3.py

…

test_synthetic_rejection_sampler_utils.py

[Model Runner V2] Enable forcing a specific acceptance rate during rejection sampling (#38045)

2026-03-26 13:38:12 -07:00

test_tree_attention.py

…