We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
8a12a8c
v0.3.4: SIMD string scanning, zero-copy decode, fast path - SIMD string scanning: AVX2 (32B/iter, x86_64), SSE2 (16B/iter, x86_64), NEON (16B/iter, aarch64), 8-byte scalar fallback for other targets. Runtime AVX2 detection with #[target_feature] for correct codegen. - Zero-copy sub-binary references for non-escaped strings >= 64 bytes. - Decode fast path: decode!/1 bypasses option parsing for no-options calls. - 2-4x faster on string-heavy payloads, 15-30% faster on small payloads vs v0.3.3.