Skip to content
conftrace_

fp8 quantization

5 papers

Explore in graph

Also known as

FP8

Co-occurring keywords · papers mentioning both

int4 quantization (2) model compression (2) int8 quantization (1) low-precision arithmetic (1) attention efficiency (1) hopper gpu (1) visual geometry grounded transformer (1) outlier smoothing (1) two-level accumulation (1) geometric perception (1)

Papers

LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging CVPR 2026 “Give Me BF16 or Give Me Death”? Accuracy-Performance Trade-Offs in LLM Quantization ACL 2025 SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization ICML 2025 FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision NeurIPS 2024 FP8 Quantization: The Power of the Exponent NeurIPS 2022