xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-03 08:55:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Remove the chunked prefill warning for LoRA (#16925)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-04-22 11:44:24 +08:00 committed by GitHub
parent 5b794cae8d
commit c9acbf1141
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
vllm/config.py
View File

@ -2686,13 +2686,6 @@ class LoRAConfig:
elif isinstance(self.lora_dtype, str):
self.lora_dtype = getattr(torch, self.lora_dtype)
def verify_with_scheduler_config(self, scheduler_config: SchedulerConfig):
# Reminder: Please update docs/source/features/compatibility_matrix.md
# If the feature combo become valid
if scheduler_config.chunked_prefill_enabled:
logger.warning("LoRA with chunked prefill is still experimental "
"and may be unstable.")
def verify_lora_support(self):
if self.long_lora_scaling_factors is not None and envs.VLLM_USE_V1:
raise ValueError(
@ -3820,8 +3813,6 @@ class VllmConfig:
if self.lora_config:
self.lora_config.verify_with_cache_config(self.cache_config)
self.lora_config.verify_with_model_config(self.model_config)
self.lora_config.verify_with_scheduler_config(
self.scheduler_config)
self.lora_config.verify_lora_support()
if self.prompt_adapter_config:
self.prompt_adapter_config.verify_with_model_config(