Woosuk Kwon c9b38be8aa

[Spec Decode] Make propose_draft_token_ids non-blocking for lower TTFT (#23041) ...

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2025-08-18 17:20:38 -07:00

..

attention

…

core

[Spec Decode] Make propose_draft_token_ids non-blocking for lower TTFT (#23041)

2025-08-18 17:20:38 -07:00

cudagraph

…

e2e

…

engine

…

entrypoints

…

kv_connector

[Spec Decode] Make propose_draft_token_ids non-blocking for lower TTFT (#23041)

2025-08-18 17:20:38 -07:00

logits_processors

…

metrics

…

sample

…

shutdown

…

spec_decode

…

structured_output

…

tpu

…

worker

…

__init__.py

…

test_async_llm_dp.py

…

test_external_lb_dp.py

…

test_hybrid_lb_dp.py

…

test_internal_lb_dp.py

…

test_kv_sharing.py

…

test_metrics_reader.py

…

test_oracle.py

…

test_request.py

…

test_serial_utils.py

…

test_utils.py

…