Skip to content

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention#27321

Open
tianleiwu wants to merge 12 commits intomainfrom
tlwu/20260211/gqa_fp8_kv_cache
Open

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention#27321
tianleiwu wants to merge 12 commits intomainfrom
tlwu/20260211/gqa_fp8_kv_cache

Commits

Commits on Feb 11, 2026

Commits on Feb 12, 2026

Commits on Feb 13, 2026

Commits on Feb 14, 2026