Hexiang Wang 48b624e4cc [BugFix] Fix implementation bug of triton rope_siso (#7082) ...

### What this PR does / why we need it?
Previously implemention of triton rope_siso missing the storage of
second half of rope results, which will result in:

1. accuracy problem in neox-style scenario
2. ub overflow in non neox-style scenario

This PR fixes it and supplement nightly test case for it.

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e

Signed-off-by: whx-sjtu <2952154980@qq.com>

2026-03-09 23:08:43 +08:00

..

e2e

[BugFix] Fix implementation bug of triton rope_siso (#7082)

2026-03-09 23:08:43 +08:00

ut

feat(attention_cp): support chunked prefill for Qwen3Next with PCP&DCP (#6900)

2026-03-09 17:55:09 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00