auto-round
feat: add NVFP4 static KV cache quantization support
#2366

Merged

feat: add NVFP4 static KV cache quantization support #2366

chensuyue merged 3 commits into main from feat/nvfp4-kv-cache

yiliu30 added this to the 0.16.0 milestone 24 days ago

yiliu30 requested a review from

n1ck-guo 24 days ago

yiliu30 requested a review from

lvliang-intel 24 days ago

yiliu30 force pushed from 73e10c8f to 6a5c7fcc 24 days ago

feat: add NVFP4 static KV cache quantization support

7d61f8a0

yiliu30 force pushed from 6a5c7fcc to 7d61f8a0 24 days ago

Merge branch 'main' into feat/nvfp4-kv-cache

9517f7c4

lvliang-intel commented on 2026-09-16

fix: address NVFP4 KV review feedback

318a8a25

lvliang-intel approved these changes on 2026-09-17

n1ck-guo approved these changes on 2026-09-17

chensuyue merged 04fca622 into main 23 days ago

chensuyue deleted the feat/nvfp4-kv-cache branch 23 days ago

Reviewers

n1ck-guo

lvliang-intel

Assignees

No one assigned

Labels

None yet

Milestone

0.16.0