openvino
[GPU] Robust INT8 dynamic quantization handling for hybrid linear-attn (GatedDeltaNet) models
#35965
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
3
Changes
View On
GitHub
[GPU] Robust INT8 dynamic quantization handling for hybrid linear-attn (GatedDeltaNet) models
#35965
andrew-k-park
merged 3 commits into
openvinotoolkit:releases/2026/2
from
andrew-k-park:gpu-dyn-qunat-linear-attn-gs128_backport
andrew-k-park
requested a review
31 days ago
andrew-k-park
requested a review
31 days ago
github-actions
added
category: GPU
andrew-k-park
removed
category: GPU
andrew-k-park
added
backport
andrew-k-park
added
category: GPU
[GPU] WA: force gs=128 dyn-quant for Mamba2 linear_attn.out_proj
a219fe42
Clarify INT8 dyn-quant vs int4 weight quantization in hybrid linear-a…
7fd59510
isanghao
commented on 2026-05-19
Apply comment
23ad183a
geunhwan
approved these changes on 2026-05-19
geunhwan
added this to the
2026.2
milestone
30 days ago
geunhwan
added
Code Freeze
geunhwan
enabled auto-merge
30 days ago
andrew-k-park
merged
27f1dbfb
into releases/2026/2
30 days ago
andrew-k-park
deleted the gpu-dyn-qunat-linear-attn-gs128_backport branch
30 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
geunhwan
isanghao
Assignees
No one assigned
Labels
category: GPU
Code Freeze
backport
Milestone
2026.2
Login to write a write a comment.
Login via GitHub