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 16, 02:00 UTC
[Ci/Build] Fix mypy errors on main (#12296)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Jan 22, 2025 at 12:06 UTC
cbdc4ad5a502f38270650a375931db439304094c
1 file changed
+5
-2
vllm/multimodal/processing.py
+5
-2
@@ -43,7 +43,7 @@ class PromptReplacementDetails:
43
"""
44
45
@staticmethod
46
- def from_seq(seq: _PromptSeq):
46
+ def from_seq(seq: _PromptSeq) -> "PromptReplacementDetails":
47
return PromptReplacementDetails(full=seq, features=seq)
48
49
@@ -132,7 +132,10 @@ class _BoundPromptSequence:
132
_token_ids: Optional[list[int]]
133
134
@staticmethod
135
- def from_seq(tokenizer: AnyTokenizer, seq: _PromptSeq):
135
+ def from_seq(
136
+ tokenizer: AnyTokenizer,
137
+ seq: _PromptSeq,
138
+ ) -> "_BoundPromptSequence":
139
return _BoundPromptSequence(
140
tokenizer=tokenizer,
141
_text=seq if isinstance(seq, str) else None,