Skip to content

[XPU]set max_num_batched_tokens=8192 #4516

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[XPU]set max_num_batched_tokens=8192 #4516

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 1 addition & 6 deletions fastdeploy/engine/args_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,6 @@
from dataclasses import fields as dataclass_fields
from typing import Any, Dict, List, Optional, Union

import paddle

from fastdeploy import envs
from fastdeploy.config import (
CacheConfig,
Expand Down Expand Up @@ -1025,10 +1023,7 @@ def create_engine_config(self, port_availability_check=True) -> FDConfig:

if self.max_num_batched_tokens is None:
if int(envs.ENABLE_V1_KVCACHE_SCHEDULER):
if paddle.is_compiled_with_xpu():
self.max_num_batched_tokens = self.max_model_len
else:
self.max_num_batched_tokens = 8192 # if set to max_model_len, it's easy to be OOM
self.max_num_batched_tokens = 8192 # if set to max_model_len, it's easy to be OOM
else:
if self.enable_chunked_prefill:
self.max_num_batched_tokens = 2048
Expand Down
Loading