EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[bugfix] ascend schedule encountered an incorrect req block length in the check_watermark_for_prefill function (#2508)

Browse Source 
### What this PR does / why we need it?
bugfix ascend schedule encountered an incorrect req block length in the
check_watermark_for_prefill function
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.10.1.1
- vLLM main:
426cc8629f

Signed-off-by: liziyu <liziyu16@huawei.com>
This commit is contained in:
liziyu
2025-09-03 16:54:39 +08:00
committed by GitHub
parent 59d23c39eb
commit 5889fa1b1c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/core/scheduler.py
View File

@@ -465,7 +465,7 @@ class AscendScheduler(Scheduler):
self.block_size) self.block_size)
req_blocks = self.kv_cache_manager.coordinator.get_blocks( req_blocks = self.kv_cache_manager.coordinator.get_blocks(
request.request_id) request.request_id)
num_new_blocks = (num_required_blocks - len(req_blocks) - num_new_blocks = (num_required_blocks - len(req_blocks[0]) -
len(computed_blocks)) len(computed_blocks))
num_evictable_computed_blocks = sum(1 for blk in computed_blocks num_evictable_computed_blocks = sum(1 for blk in computed_blocks
if blk.ref_cnt == 0) if blk.ref_cnt == 0)