Skip to content

v0.9.0 — Structured Benchmark Suite + Flash Attention + Health/Metrics API

Latest

Choose a tag to compare

@quantumnic quantumnic released this 18 Feb 21:23
· 52 commits to main since this release

What's New

⚡ Flash Attention

Memory-efficient fused attention kernel using online softmax (Dao et al., 2022). O(1) extra memory per head instead of O(seq_len). Critical for long-context inference on memory-constrained devices. Drop-in replacement with --flash-attention flag.

📊 Structured Benchmark Suite

Machine-readable JSON output for CI/CD regression testing. 6 scenarios: GGUF parse, cold/warm load, sequential streaming, forward pass estimation, cache budget analysis. Use ssd-llm bench model.gguf --json for automated performance tracking.

🏥 Health & Metrics API

Production monitoring endpoints:

  • GET /health — readiness probe (model status, uptime)
  • GET /metrics — JSON metrics (throughput, latency p50/p95/p99, cache stats, SSD I/O)
  • Prometheus-compatible text output

Stats

  • 74 tests, all passing
  • ~8200 lines of Rust
  • Full clippy-clean codebase

Next: v1.0

Production-ready release with end-to-end benchmarks against llama.cpp.