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

Support logits_soft_cap parameter in paged_attention #7704

Merged
merged 2 commits into from
Jul 17, 2024

Conversation

wonjoolee95
Copy link
Collaborator

Support logits_soft_cap parameter in paged_attention

JAX reference: jax-ml/jax@f0e36d5#diff-f1713aabe72665edd0f07fe591b1a9ff03327ca4f8d229489fa14297c25bab08

Test plan:

root@t1v-n-4989e8c7-w-0:~/pytorch/xla# python test/test_pallas.py PallasTest.test_paged_attention_wrapper_with_attn_logits_soft_cap
INFO:jax._src.xla_bridge:Unable to initialize backend 'cuda': 
INFO:jax._src.xla_bridge:Unable to initialize backend 'rocm': module 'jaxlib.xla_extension' has no attribute 'GpuAllocatorConfig'
.
----------------------------------------------------------------------
Ran 1 test in 2.782s

OK

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.

2 participants