v0.4.0

v0.4.0

✨ Added

• Added Linux event selectors with bounded capture capability (including enhancements to syscall/tracepoint/uprobes-related paths).
• Added NVTX range event definitions with bounded capture capability, supporting application-level interval timing analysis.
• Added GPU aggregate inventory capability (measure --aggregate), supporting coarse-grained inventory before precise measurement.
• Enhanced native framework symbol resolution (including observability improvements for framework scenarios).
• Added support for concurrent worker capture orchestration in multi-process scenarios (Skill/Agent workflow).

⚡ Performance

• CUPTI path optimization: only activate selected sources/callbacks, reducing capture overhead.
• Introduced incremental CUPTI snapshot streaming, improving stability under high load.
• Added filtering and boundary control for long-running framework kernel aggregation paths.

🧪 Tests & Contracts

• Added/expanded integration tests for Linux, NVTX, PyTorch, and multi-process scenarios.
• Updated protocol and JSON Schema (including aggregate inventory result structure) with contract test coverage.

📝 Docs

• Added usage guides for Linux event profiling, aggregate-first profiling, and NVTX launch injection.
• Updated Agent Skill workflow docs, emphasizing measurement paths driven by workload type and evidence.

Full Changelog: v0.3.3...v0.4.0

What's Changed

• ✨ feat: release v0.4.0 profiling primitives by @itdevwu in #30

Full Changelog: v0.3.3...v0.4.0

v0.3.3

What's Changed

• 📝 docs: route skill by workload type by @itdevwu in #24

Full Changelog: v0.3.2...v0.3.3

What's Changed

• 📝 docs: route skill by workload type by @itdevwu in #24

Full Changelog: v0.3.2...v0.3.3

v0.3.2

What's Changed

• ✨ feat: make xprobe setup skill-managed by @itdevwu in #23

Full Changelog: v0.3.1...v0.3.2

What's Changed

• ✨ feat: make xprobe setup skill-managed by @itdevwu in #23

Full Changelog: v0.3.1...v0.3.2

v0.3.1

What's Changed

• ✨ feat: improve v0.3.1 agent investigation by @itdevwu in #22

Full Changelog: v0.3.0...v0.3.1

v0.3.0

What's Changed

• ✨ feat: complete v0.3.0 capture control by @itdevwu in #18

Full Changelog: v0.2.1...v0.3.0

v0.2.1

What's Changed

• 📦 feat: improve v0.2.1 installation and onboarding by @itdevwu in #3

Full Changelog: v0.2.0...v0.2.1

v0.2.0

What's Changed

• ✨ feat: support CUDA 12 and 13 profiling by @itdevwu in #1
• 🐛 fix: use POSIX release linkage checks by @itdevwu in #2

New Contributors

• @itdevwu made their first contribution in #1

Full Changelog: v0.1.0...v0.2.0

v0.1.0

Full Changelog: https://github.com/itdevwu/xprobe/commits/v0.1.0