[V1] Add V1 support of Qwen2-VL (#12128)

Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: imkero <kerorek@outlook.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Roger Wang
2025-01-19 19:52:13 +08:00
committed by GitHub
co-authored by imkero DarkLight1337
parent edaae198e7
commit 81763c58a0
9 changed files with 291 additions and 84 deletions
+3
View File
@@ -30,6 +30,9 @@ class CachedRequestState:
num_computed_tokens: int
output_token_ids: List[int]
mrope_positions: Optional[torch.Tensor] = None
mrope_position_delta: Optional[int] = None
@property
def num_tokens(self) -> int:
return len(self.prompt_token_ids) + len(self.output_token_ids)