Wentao Ye 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

..

extract_hidden_states_integration

[Spec Decode] Add hidden states extraction system (#33736)

2026-03-02 14:29:09 -05:00

nixl_integration

[XPU] Add test script of PD disaggregation (#36434)

2026-03-09 05:50:27 +00:00

unit

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

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

__init__.py

[Attention] MLA - Flashinfer Ragged Prefill (#20034)

2025-07-10 20:17:47 -07:00