sroy745andGitHub f6778620a9 Disable spec-decode + chunked-prefill for draft models with tensor parallelism > 1 (#10136) ...

Signed-off-by: Sourashis Roy <sroy@roblox.com>

2024-11-08 15:56:18 +00:00

..

e2e

Disable spec-decode + chunked-prefill for draft models with tensor parallelism > 1 (#10136)

2024-11-08 15:56:18 +00:00

__init__.py

…

test_batch_expansion.py

…

test_dynamic_spec_decode.py

…

test_metrics.py

…

test_multi_step_worker.py

…

test_ngram_worker.py

…

test_scorer.py

…

test_spec_decode_worker.py

…

test_utils.py

…

utils.py

…