biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[LoRA] Support Quantized Adapters (#30286)

Browse Source 
Signed-off-by: Yu Gong <yu3.gong@gmail.com>
Signed-off-by: wz1qqx <ziqi.wang@novita.ai>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: wz1qqx <55830058+wz1qqx@users.noreply.github.com>
Co-authored-by: wz1qqx <ziqi.wang@novita.ai>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
yugong333
2026-02-20 19:54:35 -08:00
committed by GitHub
parent 0e22cd618b
commit a55caf6ae9
2 changed files with 1040 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/lora/ops/triton_ops/__init__.py
View File

@@ -2,6 +2,11 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm.lora.ops.triton_ops.fused_moe_lora_fp8_op import (
fused_moe_lora_expand_fp8,
fused_moe_lora_fp8,
fused_moe_lora_shrink_fp8,
)
from vllm.lora.ops.triton_ops.fused_moe_lora_op import (
fused_moe_lora,
fused_moe_lora_expand,
@@ -18,4 +23,7 @@ __all__ = [
"fused_moe_lora",
"fused_moe_lora_shrink",
"fused_moe_lora_expand",
"fused_moe_lora_fp8",
"fused_moe_lora_shrink_fp8",
"fused_moe_lora_expand_fp8",
]

1032
vllm/lora/ops/triton_ops/fused_moe_lora_fp8_op.py Normal file
View File

File diff suppressed because it is too large Load Diff