[Bugfix][Kernel]: Fix AllSpark kernel compilation errors and enable for CUDA < 12.0 #14430
Conversation
|
👋 Hi! Thank you for contributing to the vLLM project. 💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels. Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run 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 either: Add 🚀 |
wyajieha
force-pushed
the
github-yajie-as
branch
from
da0239f to
1ec6215
Compare
wyajieha
changed the title
|
Hi, @mgoin ,the CI test failed due to issues related to the docker image. Should we re-trigger the pipeline? |
|
Hi, I already retried and it failed again. Maybe you could merge with latest main and see if that helps? |
…or CUDA version <12.0 Signed-off-by: wyj371990 <[email protected]>
wyajieha
force-pushed
the
github-yajie-as
branch
from
1ec6215 to
182827b
Compare
|
Hi, @mgoin , I've merged the latest main branch, but some new unrelated CI tests are failing (doesn't seem connected to this PR). |
…or CUDA < 12.0 (vllm-project#14430) Signed-off-by: wyj371990 <[email protected]> Signed-off-by: Richard Liu <[email protected]>
…or CUDA < 12.0 (vllm-project#14430) Signed-off-by: wyj371990 <[email protected]> Signed-off-by: Louis Ulmer <[email protected]>
…or CUDA < 12.0 (vllm-project#14430) Signed-off-by: wyj371990 <[email protected]>
…or CUDA < 12.0 (vllm-project#14430) Signed-off-by: wyj371990 <[email protected]> Signed-off-by: Mu Huai <[email protected]>
3 participants
Fix AllSpark kernel compilation errors and enable kernel for CUDA version < 12.0. (As mentioned in #14157 and #12931 (comment))