xc-llm-ascend

Files

Zetong Li 4fa7cf6f50 [Bugfix] Fix problematic dummy_run & improper input_batch_size in eagle (#6517 )

### What this PR does / why we need it?
This PR aims to fix problematic dummy_run that will cause excessive npu
memory and to fix improper input_batch_size that will degrade running
performance.

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
by ci

- vLLM version: v0.15.0
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0

---------

Signed-off-by: Zetong Li <slippersss@126.com>
Signed-off-by: lilinsiman <lilinsiman@gmail.com>
Co-authored-by: lilinsiman <lilinsiman@gmail.com>

2026-02-07 09:30:10 +08:00

__init__.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8 ) (#6604 )

2026-02-07 09:16:07 +08:00

eagle_proposer.py

[Bugfix] Fix problematic dummy_run & improper input_batch_size in eagle (#6517 )

2026-02-07 09:30:10 +08:00

interface.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8 ) (#6604 )

2026-02-07 09:16:07 +08:00

medusa_proposer.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8 ) (#6604 )