Skip to content

Conversation

@mc-nv
Copy link
Contributor

@mc-nv mc-nv commented Sep 26, 2025

Update L0_multi_gpu_vllm script in order to be able access resources within container. Those resources no longer shipped with 'pytorch-triton' wheel package."

C_INCLUDE_PATH - is as system level designed variable used by gcc compiler to look up for.

TRITON_PTXAS_PATH - is a variable that has normalized name and has corresponded reference to the package that is been used and installed within container.

…within container. Those resources no longer shipped with 'pytorch-triton' wheel package.
@mc-nv mc-nv merged commit c9acf9d into r25.09 Sep 26, 2025
3 checks passed
@mc-nv mc-nv deleted the mchornyi/TPRD-1731/vllm-multi-gpu branch November 4, 2025 17:47
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.

4 participants