import torch
import torch.nn.functional as F

q = torch.randn(2, 8, 512, 64, device='cuda', dtype=torch.float16)  # [batch, heads, seq, dim]
k = torch.randn(2, 8, 512, 64, device='cuda', dtype=torch.float16)
v = torch.randn(2, 8, 512, 64, device='cuda', dtype=torch.float16)

# Automatically uses Flash Attention if available
out = F.scaled_dot_product_attention(q, k, v)

pip install flash-attn --no-build-isolation

from flash_attn import flash_attn_func

# q, k, v: [batch, seqlen, nheads, headdim]
out = flash_attn_func(q, k, v, dropout_p=0.0, causal=True)

Flash Attention Integration:
- [ ] Step 1: Check PyTorch version (≥2.2)
- [ ] Step 2: Enable Flash Attention backend
- [ ] Step 3: Verify speedup with profiling
- [ ] Step 4: Test accuracy matches baseline

python -c "import torch; print(torch.__version__)"
# Should be ≥2.2.0

pip install --upgrade torch

# 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)

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)

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")

# 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

flash-attn Library Setup:
- [ ] Step 1: Install flash-attn library
- [ ] Step 2: Modify attention code
- [ ] Step 3: Enable advanced features
- [ ] Step 4: Benchmark performance

# NVIDIA GPUs (CUDA 12.0+)
pip install flash-attn --no-build-isolation

# Verify installation
python -c "from flash_attn import flash_attn_func; print('Success')"

from flash_attn import flash_attn_func

# Input: [batch_size, seq_len, num_heads, head_dim]
# Transpose from [batch, heads, seq, dim] if needed
q = q.transpose(1, 2)  # [batch, seq, heads, dim]
k = k.transpose(1, 2)
v = v.transpose(1, 2)

out = flash_attn_func(
    q, k, v,
    dropout_p=0.1,
    causal=True,  # For autoregressive models
    window_size=(-1, -1),  # No sliding window
    softmax_scale=None  # Auto-scale
)

out = out.transpose(1, 2)  # Back to [batch, heads, seq, dim]

from flash_attn import flash_attn_func

# q: [batch, seq, num_q_heads, dim]
# k, v: [batch, seq, num_kv_heads, dim]  # Fewer KV heads
out = flash_attn_func(q, k, v)  # Automatically handles MQA

# 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
)

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")

FP8 Setup:
- [ ] Step 1: Verify H100 GPU available
- [ ] Step 2: Install flash-attn with FP8 support
- [ ] Step 3: Convert inputs to FP8
- [ ] Step 4: Run with FP8 attention

nvidia-smi --query-gpu=name --format=csv
# Should show "H100" or "H800"

pip install flash-attn --no-build-isolation
# FP8 support included for H100

import torch

q = torch.randn(2, 4096, 32, 64, device='cuda', dtype=torch.float16)
k = torch.randn(2, 4096, 32, 64, device='cuda', dtype=torch.float16)
v = torch.randn(2, 4096, 32, 64, device='cuda', dtype=torch.float16)

# Convert to float8_e4m3 (FP8)
q_fp8 = q.to(torch.float8_e4m3fn)
k_fp8 = k.to(torch.float8_e4m3fn)
v_fp8 = v.to(torch.float8_e4m3fn)

from flash_attn import flash_attn_func

# FlashAttention-3 automatically uses FP8 kernels on H100
out = flash_attn_func(q_fp8, k_fp8, v_fp8)
# Result: ~1.2 PFLOPS, 1.5-2x faster than FP16

pip install flash-attn --no-build-isolation

conda install cuda -c nvidia
pip install flash-attn --no-build-isolation

import torch
print(torch.cuda.get_device_capability())
# Should be ≥(7, 5) for Turing+

q = q.to(torch.float16)  # Or torch.bfloat16