Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
python -c "import torch; print(torch.__version__)"
# Should be ≥2.2.0
If <2.2, upgrade:
pip install --upgrade torch
Step 2: Enable Flash Attention backend
Replace standard attention:
# Before (standard attention)
attn_weights = torch.softmax(q @ k.transpose(-2, -1) / math.sqrt(d_k), dim=-1)
out = attn_weights @ v
# After (Flash Attention)
import torch.nn.functional as F
out = F.scaled_dot_product_attention(q, k, v, attn_mask=mask)
Force Flash Attention backend:
with torch.backends.cuda.sdp_kernel(
enable_flash=True,
enable_math=False,
enable_mem_efficient=False
):
out = F.scaled_dot_product_attention(q, k, v)
Step 3: Verify speedup with profiling
import torch.utils.benchmark as benchmark
def test_attention(use_flash):
q, k, v = [torch.randn(2, 8, 2048, 64, device='cuda', dtype=torch.float16) for _ in range(3)]
if use_flash:
with torch.backends.cuda.sdp_kernel(enable_flash=True):
return F.scaled_dot_product_attention(q, k, v)
else:
attn = (q @ k.transpose(-2, -1) / 8.0).softmax(dim=-1)
return attn @ v
# Benchmark
t_flash = benchmark.Timer(stmt='test_attention(True)', globals=globals())
t_standard = benchmark.Timer(stmt='test_attention(False)', globals=globals())
print(f"Flash: {t_flash.timeit(100).mean:.3f}s")
print(f"Standard: {t_standard.timeit(100).mean:.3f}s")
Expected: 2-4x speedup for sequences >512 tokens.
Step 4: Test accuracy matches baseline
# Compare outputs
q, k, v = [torch.randn(1, 8, 512, 64, device='cuda', dtype=torch.float16) for _ in range(3)]
# Flash Attention
out_flash = F.scaled_dot_product_attention(q, k, v)
# Standard attention
attn_weights = torch.softmax(q @ k.transpose(-2, -1) / 8.0, dim=-1)
out_standard = attn_weights @ v
# Check difference
diff = (out_flash - out_standard).abs().max()
print(f"Max difference: {diff:.6f}")
# Should be <1e-3 for float16
Workflow 2: Use flash-attn library for advanced features
For multi-query attention, sliding window, or H100 FP8.
# Only attend to window of 256 tokens before/after
out = flash_attn_func(
q, k, v,
window_size=(256, 256), # (left, right) window
causal=True
)
Step 4: Benchmark performance
import torch
from flash_attn import flash_attn_func
import time
q, k, v = [torch.randn(4, 4096, 32, 64, device='cuda', dtype=torch.float16) for _ in range(3)]
# Warmup
for _ in range(10):
_ = flash_attn_func(q, k, v)
# Benchmark
torch.cuda.synchronize()
start = time.time()
for _ in range(100):
out = flash_attn_func(q, k, v)
torch.cuda.synchronize()
end = time.time()
print(f"Time per iteration: {(end-start)/100*1000:.2f}ms")
print(f"Memory allocated: {torch.cuda.max_memory_allocated()/1e9:.2f}GB")
