[Performance] Add Triton kernel for Gemma3n sparse GELU (#48498)
Signed-off-by: BWAAEEEK <jooho414@gmail.com> Co-authored-by: Andreas Karatzas <akaratza@amd.com> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
co-authored by
Andreas Karatzas
Cyrus Leung
parent
e6b4e47d2d
commit
78e84261ab
@@ -2,6 +2,6 @@
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""Kernel implementations for vLLM."""
|
||||
|
||||
from . import aiter_ops, oink_ops, vllm_c
|
||||
from . import aiter_ops, oink_ops, triton, vllm_c
|
||||
|
||||
__all__ = ["vllm_c", "aiter_ops", "oink_ops"]
|
||||
__all__ = ["vllm_c", "aiter_ops", "oink_ops", "triton"]
|
||||
|
||||
Reference in New Issue
Block a user