Skip to content
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.

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

Add FlashInfer to default Dockerfile #6172

Merged
merged 1 commit into from
Jul 8, 2024

Conversation

simon-mo
Copy link
Collaborator

@simon-mo simon-mo commented Jul 6, 2024

Closes #6169

Testing with

docker run --gpus all -p 8000:8000 -e HF_TOKEN --ipc=host --env "VLLM_ATTENTION_BACKEND=FLASHINFER" -v /data/xmo/hub:/root/.cache/huggingface vllm/vllm-openai --model google/gemma-2-9b-it
$ curl http://localhost:8000/v1/completions  -H "Content-Type: application/json"      -d '{
"model": "google/gemma-2-9b-it",
"prompt":"Who won the world series in 2020?",
"max_tokens": 100,
"ignore_eos": true
}'
{"id":"cmpl-8ce64ceae52449e2b04988b08f3f42f9","object":"text_completion","created":1720253967,"model":"google/gemma-2-9b-it","choices":[{"index":0,"text":"\n\nThe **Los Angeles Dodgers** won the World Series in 2020. \n\\\\\n  \\\\\n\n\n\\\\\n\\\\\n\\\n\n\\\\\n\\\\\n\n\n\n\n.\n\n\n'.\n\n\n\n\n\n **\n\n\n\n\n。","logprobs":null,"finish_reason":"length","stop_reason":null}],"usage":{"prompt_tokens":13,"total_tokens":113,"completion_tokens":100}}(miniconda3) (base) [xmo@flow-matic:/data/xmo/vllm]$ 

The docker image for vllm/vllm-openai:latest and vllm/vllm-openai:v0.5.1 has been built and updated. This doesn't effect the wheel build.

Copy link
Collaborator

@WoosukKwon WoosukKwon left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

Copy link
Contributor

@zhyncs zhyncs left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FlashInfer 0.9.0 has been optimized for GQA, maybe we can wait until version 0.9.0 is released before integrating it into the Dockerfile.

@simon-mo simon-mo merged commit 4f0e0ea into vllm-project:main Jul 8, 2024
70 checks passed
@simon-mo
Copy link
Collaborator Author

simon-mo commented Jul 8, 2024

We already released v0.8.0 and will be able to update right after!

@zhyncs
Copy link
Contributor

zhyncs commented Jul 8, 2024

ok

dtrifiro pushed a commit to opendatahub-io/vllm that referenced this pull request Jul 17, 2024
xjpang pushed a commit to xjpang/vllm that referenced this pull request Jul 24, 2024
Alvant pushed a commit to compressa-ai/vllm that referenced this pull request Oct 26, 2024
Signed-off-by: Alvant <alvasian@yandex.ru>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Bug]: TypeError: 'NoneType' object is not callable when loading Gemma 2 9B with new 0.5.1 version
3 participants