biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Attention] MLA with chunked prefill (#12639)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Patrick Horn <patrick.horn@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson
2025-02-21 18:30:12 -05:00
committed by GitHub
parent 900edbfa48
commit 288cc6c234
18 changed files with 1910 additions and 1275 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
vllm/config.py
View File

@@ -3332,19 +3332,6 @@ class VllmConfig:
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
self.scheduler_config.max_num_batched_tokens = max(
self.scheduler_config.max_model_len,
_DEFAULT_MAX_NUM_BATCHED_TOKENS)
if self.cache_config is not None:
self.cache_config.enable_prefix_caching = False
if not self.instance_id:
self.instance_id = random_uuid()[:5]