[bugfix] A2 Environment Pooling for Memcache Compatibility (#5601)

### What this PR does / why we need it?
When running memcache in the A2 environment, the logic for registering
memory needs to be added. Additionally, there is a link establishment
conflict between memcache and HCCS during initialization in A2, so the
link should be established in advance.

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

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
7157596103

---------

Signed-off-by: fangjianwei <f30058701@china.huawei.com>
Co-authored-by: fangjianwei <f30058701@china.huawei.com>
This commit is contained in:
DreamerLeader
2026-01-13 09:07:38 +08:00
committed by GitHub
parent fe251a2efe
commit db7cf9b0ca
3 changed files with 34 additions and 7 deletions

View File

@@ -82,7 +82,10 @@ class KVPoolScheduler:
if num_external_hit_tokens == request.num_tokens:
num_external_hit_tokens -= 1
need_to_allocate = num_external_hit_tokens - num_computed_tokens
if num_external_hit_tokens < num_computed_tokens:
need_to_allocate = 0
else:
need_to_allocate = num_external_hit_tokens - num_computed_tokens
logger.info(
"Reqid: %s, Total tokens %d, kvpool hit tokens: %d, need to load: %d",