xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-09-09 00:27:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[misc] Do not allow to use lora with chunked prefill. (#5538)

Browse Source 
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
SangBin Cho 2024-06-15 23:59:36 +09:00 committed by GitHub
parent 81fbb3655f
commit e691918e3b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config.py
View File

@ -1092,6 +1092,8 @@ class LoRAConfig:
"Due to limitations of the custom LoRA CUDA kernel, " "Due to limitations of the custom LoRA CUDA kernel, "
"max_num_batched_tokens must be <= 65528 when " "max_num_batched_tokens must be <= 65528 when "
"LoRA is enabled.") "LoRA is enabled.")
if scheduler_config.chunked_prefill_enabled:
raise ValueError("LoRA is not supported with chunked prefill yet.")
@dataclass @dataclass