Wentao YeandOr Ozeri a8ff2cca92 [Perf] Optimize scheduler overhead for PD disaggregation, around 5% E2E perf improvement (#35781) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>

2026-03-10 21:25:30 -07:00

..

__init__.py

…

test_async_scheduler.py

…

test_encoder_cache_manager.py

…

test_kv_cache_metrics.py

…

test_kv_cache_utils.py

perf: add __slots__ to KVCacheBlock (#36164)

2026-03-05 22:04:09 -08:00

test_kv_sharing.py

…

test_output.py

…

test_prefix_caching.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00

test_priority_scheduler_random.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00

test_repetition_detection.py

[Core] Add optional flags to check for repetitive token patterns in engine output (#35451)

2026-03-03 12:23:25 +08:00

test_reset_prefix_cache_e2e.py

…

test_scheduler_e2e.py

…

test_scheduler.py

[Perf] Optimize scheduler overhead for PD disaggregation, around 5% E2E perf improvement (#35781)

2026-03-10 21:25:30 -07:00

test_single_type_kv_cache_manager.py

…

utils.py

[V0 Deprecation] Remove unused swap_space parameter (#36216)

2026-03-07 22:09:55 +08:00