Add TMA support to fused_moe_lora kernel (#32195)

Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
gnovack
2026-03-01 10:55:25 +08:00
committed by GitHub
co-authored by Jee Jee Li
parent e3eb146f7a
commit 3ecd0bf9fc
5 changed files with 278 additions and 51 deletions
+13
View File
@@ -0,0 +1,13 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import torch
from vllm.triton_utils import triton
def set_triton_allocator(device: torch.device):
def alloc_fn(size: int, alignment: int, stream: int | None):
return torch.empty(size, device=device, dtype=torch.int8)
triton.set_allocator(alloc_fn)