SIGN IN SIGN UP

A high-throughput and memory-efficient inference and serving engine for LLMs

0 0 122 Python

[Feature] Batch Invariant for R1 TP 8 on Blackwell (#27229)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
W
Wentao Ye committed
86ed77022db254cab1386c211f150d3840af156c
Parent: aa1356e
Committed by GitHub <noreply@github.com> on 10/21/2025, 5:25:55 PM