Skip to content

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

Merged
tianleiwu merged 12 commits into
mainfrom
tlwu/20260211/gqa_fp8_kv_cache
Feb 18, 2026
Merged

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention#27321
tianleiwu merged 12 commits into
mainfrom
tlwu/20260211/gqa_fp8_kv_cache

fix build

2a25780
Select commit
Loading
Failed to load commit list.
Azure Pipelines / Windows ARM64 QNN CI Pipeline succeeded Feb 14, 2026 in 37m 15s

Build #20260213.14 succeeded

Details

Tests

  • Failed: 0 (0.00%)
  • Passed: 86 (96.63%)
  • Other: 3 (3.37%)
  • Total: 89