xc-llm-ascend

Files

panchao-hub 8c2c82f3e1 [Bugfix] Fix the moe_forward error when setting enable_static_kernel … (#6964 )

### What this PR does / why we need it?
Fix the moe_forward error when setting enable_static_kernel to true.
When static kernels are enabled, the forward pass runs twice
(compilation + capture), causing moe_layer_index to overflow. Wrap the
index to prevent out-of-bounds errors.

### Does this PR introduce _any_ user-facing change?
None

### How was this patch tested?
CI passed with new added test

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

Signed-off-by: p00465316 <panchao13@huawei.com>
Co-authored-by: p00465316 <panchao13@huawei.com>

2026-03-06 10:36:10 +08:00

__init__.py

[Refactor] [MoE] Rename moe-related classes & files (#3646 )

2025-10-25 11:22:03 +08:00

comm_utils.py

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #11 ) (#6176 )

2026-02-06 15:28:49 +08:00

experts_selector.py

[Refact]Refact MLA/SFA weight prefetch to consist with moe weight prefetch (#6629 )

2026-02-10 14:14:37 +08:00

fused_moe.py

[Bugfix] Fix the moe_forward error when setting enable_static_kernel … (#6964 )