Benjamin ChislettandGitHub af3162d3aa [Spec Decode] Unified Parallel Drafting (#32887) ...

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>

2026-02-05 12:37:18 -05:00

..

__init__.py

Test: added acceptance length tests (#32030)

2026-01-20 18:55:15 +00:00

test_acceptance_length.py

move spec decode slow test to test_areas.yaml (#33365)

2026-02-02 06:28:36 -08:00

test_eagle.py

[Spec Decode] Unified Parallel Drafting (#32887)

2026-02-05 12:37:18 -05:00

test_max_len.py

[Attention] Update tests to remove deprecated env vars (#30563)

2025-12-17 09:49:59 -08:00

test_mtp.py

[Spec Decode] Unified Parallel Drafting (#32887)

2026-02-05 12:37:18 -05:00

test_ngram.py

[Cleanup] Remove obsolete spec decoding compatibility logic (#32003)

2026-01-09 05:44:18 +00:00

test_speculators_eagle3.py

[Rocm][CI] Fix test_speculator_eagle3 by skipping the CompressedTensorw4a16 Model (#30001)

2025-12-04 07:52:28 +00:00

test_tree_attention.py

[Performance] Split FlashAttn attention and cache update (#25954)

2026-01-23 17:28:06 -08:00