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

Update FLEX in Deepspeed README (#10774)

Browse source 
* Update FLEX in Deepspeed README

* Update README.md
This commit is contained in:
Heyang Sun 2024-04-17 09:28:24 +08:00 committed by GitHub
parent c41730e024
commit 26cae0a39c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 8 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
python/llm/example/GPU/Deepspeed-AutoTP/README.md
View file

@ -49,6 +49,14 @@ bash run_vicuna_33b_arc_2_card.sh
> **Note**: You could change `NUM_GPUS` to the number of GPUs you have on your machine. And you could also specify other low bit optimizations through `--low-bit`.
- Run Mistral-7B-Instruct on two cards of Intel Data Center GPU Flex
```bash
bash run_mistral_7b_instruct_flex_2_card.sh
```
> **Note**: You could change `NUM_GPUS` to the number of GPUs you have on your machine. And you could also specify other low bit optimizations through `--low-bit`.
### 3. Sample Output
```bash