Zhang-Bryan 804a9ec4e6 [Fusion] Add rmsnorm dynamic quant fusion pass (#6274) ...

### What this PR does / why we need it?

This PR introduces four new patterns to support the fusion of RMSNorm
and DynamicQuant operators. After replacing the fusion operators, the
execution time has been reduced from 22.8us to 16.9us.

### Does this PR introduce _any_ user-facing change?

N/A

### How was this patch tested?


- vLLM version: v0.14.1
- vLLM main:
d7de043d55

Signed-off-by: Bryan <250470359+Zhang-Bryan@users.noreply.github.com>

2026-02-04 15:53:53 +08:00

..

npugraph_ex_passes

[bugfix][npugraph_ex]duplicate pattern issue (#6513)

2026-02-04 08:49:13 +08:00

passes

[Fusion] Add rmsnorm dynamic quant fusion pass (#6274)

2026-02-04 15:53:53 +08:00

__init__.py

[Bugfix] add compilation/__init__.py to fix import error (#1152)

2025-06-10 17:14:25 +08:00

acl_graph.py

[Bugfix] Synchronize only the current stream to avoid device sync (#6432)

2026-02-04 10:59:45 +08:00

compiler_interface.py

[e2e Test][npugraph_ex]add static kernel e2e test case (#6320)

2026-01-30 16:24:48 +08:00

graph_fusion_pass_manager.py

[Fusion] [Graph]Add Matmul Allreduce Rmsnorm fusion Pass (#5034)

2026-01-19 09:28:07 +08:00

npu_graph_ex_pass_manager.py

[Graph][Fusion] Add MatmulAllReduceAddRMSNorm graph fusion for npugraph_ex. (#6006)

2026-01-27 16:41:48 +08:00