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

[Hardware][CPU] Multi-LoRA implementation for the CPU backend (#11100)

Browse Source 
Signed-off-by: Akshat Tripathi <akshat@krai.ai>
Signed-off-by: Oleg Mosalov <oleg@krai.ai>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Oleg Mosalov <oleg@krai.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Akshat Tripathi
2025-01-12 13:01:52 +00:00
committed by GitHub
parent f967e51f38
commit 8bddb73512
25 changed files with 855 additions and 193 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/lora/punica_wrapper/punica_gpu.py
View File

@@ -12,11 +12,11 @@ import torch
from vllm.triton_utils import HAS_TRITON
if HAS_TRITON:
from vllm.lora.ops.bgmv_expand import bgmv_expand
from vllm.lora.ops.bgmv_expand_slice import bgmv_expand_slice
from vllm.lora.ops.bgmv_shrink import bgmv_shrink
from vllm.lora.ops.sgmv_expand import sgmv_expand
from vllm.lora.ops.sgmv_shrink import sgmv_shrink
from vllm.lora.ops.triton_ops import bgmv_expand
from vllm.lora.ops.triton_ops import bgmv_expand_slice
from vllm.lora.ops.triton_ops import bgmv_shrink
from vllm.lora.ops.triton_ops import sgmv_expand
from vllm.lora.ops.triton_ops import sgmv_shrink
from .punica_base import PunicaWrapperBase