Skip to content

Paro inference#2638

Draft
Qubitium wants to merge 5 commits intomainfrom
paro-inference
Draft

Paro inference#2638
Qubitium wants to merge 5 commits intomainfrom
paro-inference

Conversation

@Qubitium
Copy link
Copy Markdown
Collaborator

make the kernel zoom zoom

return fp32_reduce_kernel(input, qweight, scales, qzeros, split_k_iters)

return awq_ext.gemm_forward_cuda(input, qweight, scales, qzeros, split_k_iters)
awq_ext = _AwqExtensionCompat() if awq_runtime_available() else None

return awq_ext.gemm_forward_cuda(input, qweight, scales, qzeros, split_k_iters)
awq_ext = _AwqExtensionCompat() if awq_runtime_available() else None
msg = awq_runtime_error()
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.

1 participant