xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-08 18:17:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

remove

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-09-18 14:35:25 -07:00
parent 330058f9b8
commit 82e591f7eb
1 changed files with 1 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/v1/worker/gpu/states.py
View File

@ -1,7 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from dataclasses import dataclass
from typing import Optional, Union
from typing import Optional
import numba
import numba.types as types
@ -131,16 +131,6 @@ class RequestState:
needs_prompt_logprobs = sampling_params.prompt_logprobs is not None
self.needs_prompt_logprobs[req_idx] = needs_prompt_logprobs
def append_token_ids(
self,
req_idx: int,
token_ids: Union[list[int], np.ndarray],
) -> None:
start_idx = self.num_tokens[req_idx]
end_idx = start_idx + len(token_ids)
self.token_ids[req_idx, start_idx:end_idx] = token_ids
self.num_tokens[req_idx] = end_idx
def remove_request(self, req_id: str) -> None:
req_idx = self.req_id_to_index.pop(req_id, None)
if req_idx is None: