fetch_ml/internal/worker
Jeremie Fraeys 17170667e2
feat(worker): improve lifecycle management and vLLM plugin
Lifecycle improvements:
- runloop.go: refined state machine with better error recovery
- service_manager.go: service dependency management and health checks
- states.go: add states for capability advertisement and draining

Container execution:
- container.go: improved OCI runtime integration with supply chain checks
- Add image verification and signature validation
- Better resource limits enforcement for GPU/memory

vLLM plugin updates:
- vllm.go: support for vLLM 0.3+ with new engine arguments
- Add quantization-aware scheduling (AWQ, GPTQ, FP8)
- Improve model download and caching logic

Configuration:
- config.go: add capability advertisement configuration
- snapshot_store.go: improve snapshot management for checkpointing
2026-03-12 12:05:02 -04:00
..
errors feat(worker): integrate scheduler endpoints and security hardening 2026-02-26 12:06:16 -05:00
execution refactor(scheduler,worker): improve service management and GPU detection 2026-03-08 13:03:15 -04:00
executor feat(worker): improve lifecycle management and vLLM plugin 2026-03-12 12:05:02 -04:00
integrity refactor(scheduler,worker): improve service management and GPU detection 2026-03-08 13:03:15 -04:00
interfaces feat(worker): integrate scheduler endpoints and security hardening 2026-02-26 12:06:16 -05:00
lifecycle feat(worker): improve lifecycle management and vLLM plugin 2026-03-12 12:05:02 -04:00
plugins feat(worker): improve lifecycle management and vLLM plugin 2026-03-12 12:05:02 -04:00
process refactor(scheduler,worker): improve service management and GPU detection 2026-03-08 13:03:15 -04:00
tenant refactor(scheduler,worker): improve service management and GPU detection 2026-03-08 13:03:15 -04:00
artifacts.go feat(worker): integrate scheduler endpoints and security hardening 2026-02-26 12:06:16 -05:00
config.go feat(worker): improve lifecycle management and vLLM plugin 2026-03-12 12:05:02 -04:00
factory.go feat(worker): integrate scheduler endpoints and security hardening 2026-02-26 12:06:16 -05:00
gpu_detector.go feat(worker): refactor GPU detection with macOS Metal support 2026-03-12 12:02:41 -04:00
gpu_detector_mock.go feat(worker): refactor GPU detection with macOS Metal support 2026-03-12 12:02:41 -04:00
gpu_macos.go feat(worker): refactor GPU detection with macOS Metal support 2026-03-12 12:02:41 -04:00
gpu_macos_stub.go feat: native GPU detection and NVML bridge for macOS and Linux 2026-02-21 17:59:59 -05:00
gpu_nvml_native.go feat: native GPU detection and NVML bridge for macOS and Linux 2026-02-21 17:59:59 -05:00
gpu_nvml_stub.go feat(worker): integrate scheduler endpoints and security hardening 2026-02-26 12:06:16 -05:00
native_bridge.go refactor(worker): update worker tests and native bridge 2026-02-23 18:04:22 -05:00
native_bridge_libs.go feat(security): Artifact ingestion caps enforcement 2026-02-23 19:43:28 -05:00
native_bridge_nocgo.go refactor(worker): update worker tests and native bridge 2026-02-23 18:04:22 -05:00
snapshot_store.go feat(worker): improve lifecycle management and vLLM plugin 2026-03-12 12:05:02 -04:00
worker.go refactor(scheduler,worker): improve service management and GPU detection 2026-03-08 13:03:15 -04:00