openvino
[NPUW]Optimize token rate for dynamic LoRA.
#31742
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
9
Changes
View On
GitHub
[NPUW]Optimize token rate for dynamic LoRA.
#31742
intelgaoxiong
merged 9 commits into
openvinotoolkit:master
from
intelgaoxiong:xiong/lora_opt
github-actions
added
category: NPU
github-actions
added
category: NPUW
intelgaoxiong
force pushed
from
4433602b
to
63ccf509
309 days ago
intelgaoxiong
force pushed
from
63ccf509
to
a26d147d
309 days ago
intelgaoxiong
force pushed
from
1aa323e9
to
7fe55191
304 days ago
github-actions
added
category: build
intelgaoxiong
force pushed
from
1c470b91
to
0c67db58
303 days ago
github-actions
removed
category: build
intelgaoxiong
marked this pull request as ready for review
303 days ago
intelgaoxiong
requested a review
303 days ago
intelgaoxiong
requested a review
303 days ago
intelgaoxiong
requested a review
from
dmatveev
303 days ago
intelgaoxiong
requested a review
from
smirnov-alexey
303 days ago
smirnov-alexey
commented on 2025-08-21
smirnov-alexey
approved these changes on 2025-08-21
Reuse infer request buffer for LoRA.
359837b2
Solved review comments in pr#31433.
145536a8
Fixed for CI.
70011f21
Set remote tensor for kvcache and prefill
4dd3d801
Choose device for pre-allocation.
7dca40b8
Move lora name matching functions to utils.
fa093a09
Move allocMem to util.
b8b06f9e
Minor change.
a3e1f918
No need to bump the serialization version.
c4d302d4
intelgaoxiong
force pushed
from
6d027ac3
to
c4d302d4
303 days ago
intelgaoxiong
enabled auto-merge
303 days ago
intelgaoxiong
merged
eac9970a
into master
303 days ago
intelgaoxiong
deleted the xiong/lora_opt branch
303 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
smirnov-alexey
dmatveev
Assignees
No one assigned
Labels
category: NPU
category: NPUW
Milestone
No milestone
Login to write a write a comment.
Login via GitHub