xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-12 17:57:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix typo in scheduler.py (requeset -> request) (#5470)

Browse Source
This commit is contained in:
Michael Goin 2024-06-12 17:59:44 -04:00 committed by GitHub
parent b8d4dfff9c
commit 94a07bbdd8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
vllm/core/scheduler.py
View File

@ -50,8 +50,8 @@ class SchedulingBudget:
""" """
token_budget: int token_budget: int
max_num_seqs: int max_num_seqs: int
_requeset_ids_num_batched_tokens: Set[str] = field(default_factory=set) _request_ids_num_batched_tokens: Set[str] = field(default_factory=set)
_requeset_ids_num_curr_seqs: Set[str] = field(default_factory=set) _request_ids_num_curr_seqs: Set[str] = field(default_factory=set)
_num_batched_tokens: int = 0 _num_batched_tokens: int = 0
_num_curr_seqs: int = 0 _num_curr_seqs: int = 0
@ -65,28 +65,28 @@ class SchedulingBudget:
return self.token_budget - self.num_batched_tokens return self.token_budget - self.num_batched_tokens
def add_num_batched_tokens(self, req_id: str, num_batched_tokens: int): def add_num_batched_tokens(self, req_id: str, num_batched_tokens: int):
if req_id in self._requeset_ids_num_batched_tokens: if req_id in self._request_ids_num_batched_tokens:
return return
self._requeset_ids_num_batched_tokens.add(req_id) self._request_ids_num_batched_tokens.add(req_id)
self._num_batched_tokens += num_batched_tokens self._num_batched_tokens += num_batched_tokens
def subtract_num_batched_tokens(self, req_id: str, def subtract_num_batched_tokens(self, req_id: str,
num_batched_tokens: int): num_batched_tokens: int):
if req_id in self._requeset_ids_num_batched_tokens: if req_id in self._request_ids_num_batched_tokens:
self._requeset_ids_num_batched_tokens.remove(req_id) self._request_ids_num_batched_tokens.remove(req_id)
self._num_batched_tokens -= num_batched_tokens self._num_batched_tokens -= num_batched_tokens
def add_num_seqs(self, req_id: str, num_curr_seqs: int): def add_num_seqs(self, req_id: str, num_curr_seqs: int):
if req_id in self._requeset_ids_num_curr_seqs: if req_id in self._request_ids_num_curr_seqs:
return return
self._requeset_ids_num_curr_seqs.add(req_id) self._request_ids_num_curr_seqs.add(req_id)
self._num_curr_seqs += num_curr_seqs self._num_curr_seqs += num_curr_seqs
def subtract_num_seqs(self, req_id: str, num_curr_seqs: int): def subtract_num_seqs(self, req_id: str, num_curr_seqs: int):
if req_id in self._requeset_ids_num_curr_seqs: if req_id in self._request_ids_num_curr_seqs:
self._requeset_ids_num_curr_seqs.remove(req_id) self._request_ids_num_curr_seqs.remove(req_id)
self._num_curr_seqs -= num_curr_seqs self._num_curr_seqs -= num_curr_seqs
@property @property