[rocm-libraries] ROCm/rocm-libraries#7723 (commit 4ed6c51)
[CK Tile] Enable LSE output for fp8bf16 V3 FMHA kernels
(#7723)
### Motivation
The V3 pipeline (qr_async_trload_v3) for fp8bf16 FMHA kernels did not
support LSE (Log-Sum-Exp) output. This PR enables LSE output support for
fp8bf16 V3 FMHA kernels, allowing users to retrieve attention statistics
alongside attention outputs.
### Technical Details
- StandardAttention: lse = softmax_scale * m + log(l)
- LogitsSoftCap: lse = (m / log2(e)) + log(l)
### Test Plan
Run FMHA forward example with fp8bf16 precision and LSE output enabled:
- Test 1: Basic LSE functionality
./build/bin/tile_example_fmha_fwd -v=1 -b=1 -h=8 -s=1024 -d=128
-prec=fp8bf16 -init=3 -qscale=1 -lse=1
- Test 2: LSE with LogitsSoftCap (CMakeList should remove Logits filter)
./build/bin/tile_example_fmha_fwd -v=1 -b=1 -h=8 -s=1024 -d=128
-prec=fp8bf16 -init=3 -qscale=1 -lse=1 -logits_soft_cap=30.0 L
ltqin committed
bf07a0150ee2325538b9458fd9b8e3efa48f9487
Parent: c1aee52
Committed by assistant-librarian[bot] <assistant-librarian[bot]@users.noreply.github.com>
on 5/28/2026, 3:58:54 PM