fetch_ml/internal/worker/executor
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
..
adapter.go refactor: Implement TaskExecutorAdapter and Worker.runningCount() 2026-02-17 16:15:41 -05:00
container.go feat(worker): improve lifecycle management and vLLM plugin 2026-03-12 12:05:02 -04:00
local.go feat(worker): integrate scheduler endpoints and security hardening 2026-02-26 12:06:16 -05:00
runner.go refactor(scheduler,worker): improve service management and GPU detection 2026-03-08 13:03:15 -04:00