Skip to content

GitLab

Commit 96bfa3ce authored by gaoqiong's avatar gaoqiong
Browse files

增加blockint8支持优化

parent 5f15bdb5
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
vllm/utils.py
View file @ 96bfa3ce
...@@ -1641,6 +1641,8 @@ class W8a8GetCacheJSON: ...@@ -1641,6 +1641,8 @@ class W8a8GetCacheJSON:
def get_blockint8json_name(self,n,k,block_n,block_k): def get_blockint8json_name(self,n,k,block_n,block_k):
from vllm.platforms import current_platform from vllm.platforms import current_platform
device_name = current_platform.get_device_name().replace(" ", "_") device_name = current_platform.get_device_name().replace(" ", "_")
if 'K100_AI' in device_name:
device_name='K100_AI'
return self.triton_json_dir+f"/linear_{n}_{k}_block[{block_n},{block_k}]_{device_name}.json" return self.triton_json_dir+f"/linear_{n}_{k}_block[{block_n},{block_k}]_{device_name}.json"
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment