[None][doc] GVR V2: Self-Sampling and Multi-Thresholding for Faster Exact Top-K - #19244

Merged

longcheng-nv merged 33 commits into

NVIDIA:mainfrom

longcheng-nv:docs/gvr-v2-self-sampling-topk

Sep 22, 2026

Commits on Sep 16, 2026

[None][doc] Explain GVR V2 self-sampling and multi-threshold Top-K
longcheng-nv
committed
fcbb1ea
[None][doc] Add DeepSelect FP32 speedup heatmap to GVR V2 blog
longcheng-nv
committed
329cc14
[None][doc] Keep GVR V2 blog focused on FP32 comparisons
longcheng-nv
committed
c747dc3
[None][doc] Compare average and peak reach of GVR V2 Pareto curves
longcheng-nv
committed
02fbcf8
[None][doc] Explain shared GVR V2 kernel integration for decode and prefill
longcheng-nv
committed
73620c2
[None][doc] Clarify GVR V2 narrative with recovery and integration diagrams
longcheng-nv
committed
a891ef1

Commits on Sep 17, 2026

Commits on Sep 18, 2026

Commits on Sep 19, 2026

Commits on Sep 21, 2026

[None][doc] Treat JSON blog data as downloadable assets
longcheng-nv
committed
b157334

Commits on Sep 22, 2026