A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 12:15 UTC
Add missing class docstring for `PromptAdapterConfig` (#17302)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Apr 28, 2025 at 12:06 UTC
fb1c933adefe7f09c790a49a38fe9921e15bd51a
1 file changed
+2
vllm/config.py
+2
@@ -2679,6 +2679,8 @@ class LoRAConfig:
2679
@config
2680
@dataclass
2681
class PromptAdapterConfig:
2682
+ """Configuration for PromptAdapters."""
2683
+
2684
max_prompt_adapters: int = 1
2685
"""Max number of PromptAdapters in a batch."""
2686
max_prompt_adapter_token: int = 0