-
-
Notifications
You must be signed in to change notification settings - Fork 5.7k
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
[Bugfix] Fix spurious "No compiled cutlass_scaled_mm ..." for W8A8 on Turing #9487
[Bugfix] Fix spurious "No compiled cutlass_scaled_mm ..." for W8A8 on Turing #9487
Conversation
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
0911570
to
fd80ce5
Compare
27bbd08
to
20dac77
Compare
20dac77
to
4239dfe
Compare
… Turing (vllm-project#9487) Signed-off-by: charlifu <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: Alvant <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: Erkin Sagiroglu <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: Amit Garg <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: qishuai <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: NickLucche <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: NickLucche <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: Sumit Dubey <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: Maxime Fournioux <[email protected]>
… Turing (vllm-project#9487) Signed-off-by: Tyler Michael Smith <[email protected]>
FIX #9419
Missing early return means we error out after running the kernel
(Plus fix some message spacing when building on Turing system)
Tested using a NVidia T4 GCP instance