Skip to content

[#18658][fix] Dequantize FP8 block-scaled weights for unquantized DeepSeek-V3.2/GLM indexer projections - #18665

Open
PierreLeGuen wants to merge 2 commits into
NVIDIA:mainfrom
PierreLeGuen:fix/dsa-indexer-fp8-dequant
Open

PierreLeGuen wants to merge 2 commits into
NVIDIA:mainfrom
PierreLeGuen:fix/dsa-indexer-fp8-dequant

Commits

  1. Commits on Sep 3, 2026

  2. Commits on Sep 7, 2026