[Perf] FP8 FlashInfer Attn for ViT (#38065)

Signed-off-by: Zhanda Zhu <zhandazhu@gmail.com>
Co-authored-by: Yubo Gao <ybgao-nvidia@users.noreply.github.com>
This commit is contained in:
Zhanda Zhu
2026-04-27 13:44:15 +08:00
committed by GitHub
co-authored by Yubo Gao
parent 592ae6805c
commit 5d5c776444
18 changed files with 1829 additions and 49 deletions
+1
View File
@@ -20,6 +20,7 @@ The following are the supported quantization formats for vLLM:
- [AMD Quark](quark.md)
- [Quantized KV Cache](quantized_kvcache.md)
- [TorchAO](torchao.md)
- [FP8 ViT Encoder Attention](fp8_vit_attn.md)
## Supported Hardware