Qiu 7c210225a2 [Perf][PCP][DCP] add multi-stream for GQA to enable computation-communication overlap (#5382) ...

### What this PR does / why we need it?
This PR adds multi-stream for GQA to enable computation-communication
overlap. For chunked prefill, we reduce TTFT by approximately 4%.

### Does this PR introduce _any_ user-facing change?
No

- vLLM version: release/v0.13.0
- vLLM main:
bc0a5a0c08

---------

Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>

2026-01-04 16:33:18 +08:00

..

__init__.py

[Core] Make V1 work and enable V1 engine test (#389)

2025-03-28 19:34:23 +08:00

attention_cp.py

[Perf][PCP][DCP] add multi-stream for GQA to enable computation-communication overlap (#5382)

2026-01-04 16:33:18 +08:00

attention_mask.py

[feature] fia support sliding windows (#5239)

2025-12-29 14:56:25 +08:00

attention_v1.py

[Feat][main] Supported to use full-graph with Qwen3-Next-MTP (#5477)

2026-01-04 12:03:21 +08:00

common_cp.py

[Refactor]5/N Extract common code of mla_v1.py & extract mla_cp (#5097)

2025-12-24 10:25:19 +08:00

mla_cp.py

[refactor] refactor model runner capture model (#5230)

2025-12-30 08:32:14 +08:00

mla_v1.py

[P/D] Improve the performance of Layerwise Connector (#5303)

2025-12-31 15:09:01 +08:00

sfa_v1.py

[refactor] refactor model runner capture model (#5230)

2025-12-30 08:32:14 +08:00

utils.py

[Perf][PCP][DCP] add multi-stream for GQA to enable computation-communication overlap (#5382)

2026-01-04 16:33:18 +08:00