kv_heads = 4
head_size = 8

standard_keys = kv_heads * head_size
standard_values = kv_heads * head_size
standard_total = standard_keys + standard_values

mla_latent = 8
mla_rotary_key = 4
mla_total = mla_latent + mla_rotary_key

print("standard cache:", standard_keys, "key +", standard_values, "value")
print("MLA cache:", mla_latent, "latent +", mla_rotary_key, "rotary key")
print("stored scalars per token:", standard_total, "->", mla_total)
print(f"example reduction: {standard_total / mla_total:.2f}x")

# Output:
"""
standard cache: 32 key + 32 value
MLA cache: 8 latent + 4 rotary key
stored scalars per token: 64 -> 12
example reduction: 5.33x
"""