SIGN IN SIGN UP

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

0 0 122 Python

[Feature] Batch Invariant: Support DeepGEMM and Blackwell (#27127)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
W
Wentao Ye committed
245e4f2c01d19a567742fee4117badf1f6027da0
Parent: 1d165d6
Committed by GitHub <noreply@github.com> on 10/18/2025, 1:28:05 PM