ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Update README.md (#13104)

Browse source
This commit is contained in:
Guancheng Fu 2025-04-24 10:21:17 +08:00 committed by GitHub
parent 908fdb982e
commit 0cfdd399e7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
python/llm/example/GPU/vLLM-Serving/README.md
View file

@ -64,6 +64,9 @@ pip install ray
export USE_XETLA=OFF export USE_XETLA=OFF
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=2 export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=2
export SYCL_CACHE_PERSISTENT=1 export SYCL_CACHE_PERSISTENT=1
# If you are using woq_int4, be sure to setup the following environment variable based on the cards you want to use:
export ONEAPI_DEVICE_SELECTOR=level_zero:0,1,2,3 # In case of four cards
``` ```
### 3. Offline inference/Service ### 3. Offline inference/Service