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

MoE model (BDRX/Mixtral) NaN when using flashinfer #547

Closed
Ying1123 opened this issue Jun 14, 2024 · 1 comment
Closed

MoE model (BDRX/Mixtral) NaN when using flashinfer #547

Ying1123 opened this issue Jun 14, 2024 · 1 comment
Assignees

Comments

@Ying1123
Copy link
Contributor

Reproduce by

python -m sglang.launch_server --model-path databricks/dbrx-instruct --tp 8 --port 30000 --mem-frac 0.8 --enable-flashinfer

and

python3 bench_sglang.py --num-questions 10
@Ying1123 Ying1123 self-assigned this Jun 14, 2024
@yzh119
Copy link
Collaborator

yzh119 commented Jun 19, 2024

dbrx uses a gqa group size of 6, it should have been supported in flashinfer-ai/flashinfer#301 (and release v0.0.5)

@Ying1123 Ying1123 closed this as completed Jul 5, 2024
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

No branches or pull requests

2 participants