xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-09 07:47:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Disable chunked prefill and/or prefix caching when MLA is enabled (#12642)

Browse Source 
From @mgoin in https://github.com/vllm-project/vllm/pull/12638

I cannot push to that branch, therefore a new PR to unblock release.

---------

Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
This commit is contained in:
Simon Mo 2025-01-31 23:46:57 -08:00 committed by GitHub
parent 1e3698393f
commit 4f4d427ac2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/config.py
View File

@ -3252,6 +3252,16 @@ class VllmConfig:
current_platform.check_and_update_config(self) current_platform.check_and_update_config(self)
# If MLA is enabled, force disable chunked prefill and prefix caching
if self.model_config and self.model_config.use_mla:
logger.info("MLA is enabled; forcing chunked prefill and prefix "
"caching to be disabled.")
self.scheduler_config.enable_chunked_prefill = False
self.scheduler_config.chunked_prefill_enabled = False
if self.cache_config is not None:
self.cache_config.enable_prefix_caching = False
if not self.instance_id: if not self.instance_id:
self.instance_id = random_uuid()[:5] self.instance_id = random_uuid()[:5]