Commit Graph

13 Commits

Author SHA1 Message Date
Gitea Actions
9bf987888c chore: bump version to 0.1.14 2026-04-16 16:57:24 +03:00
Gitea Actions
357f858a29 chore: bump version to 0.1.12 2026-04-16 15:47:21 +03:00
Gitea Actions
7ece281617 chore: bump version to 0.1.10 2026-04-16 15:06:18 +03:00
Gitea Actions
9fa51ad874 chore: bump version to 0.1.8 2026-04-16 10:56:07 +00:00
Gitea Actions
2ce1060cb8 chore: bump version to 0.1.7 2026-04-16 13:25:34 +03:00
Gitea Actions
52c8b4c983 chore: bump version to 0.1.5 2026-04-16 13:01:42 +03:00
Gitea Actions
f161412f91 chore: bump version to 0.1.3 2026-04-16 11:41:11 +03:00
Gitea Actions
7c60af3464 chore: bump version to 0.1.2 2026-04-16 11:03:29 +03:00
6c238f4557 refactor: rename cortex-neuron binary and crate to neuron
All checks were successful
CI / Format, lint, build, test (push) Successful in 2m28s
CI / Build SRPM (push) Has been skipped
CI / Publish to COPR (push) Has been skipped
Package name, lib name, and binary all now just "neuron" without
the cortex- prefix.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 15:51:15 +03:00
e42e8ee81f refactor: cortex talks to neurons instead of mistral.rs directly
All checks were successful
CI / Format, lint, build, test (push) Successful in 2m46s
CI / Build SRPM (push) Has been skipped
CI / Publish to COPR (push) Has been skipped
Replace NodeConfig (static vram_mb, pinned) with NeuronEndpoint.
Hardware discovery and model pinning now come from neuron API and
models.toml catalogue respectively.

- config.rs: nodes -> neurons, add models_config path
- catalogue.rs: ModelProfile with pinned_on, ModelCatalogue
- poller.rs: poll neuron GET /models (ModelInfo format)
- router.rs: resolve inference endpoint via neuron GET /models/{id}/endpoint
- evictor.rs: call neuron POST /models/unload
- node.rs: remove vram_mb, pinned fields (come from discovery/catalogue)
- All 22 gateway tests updated to mock neuron API
- Remove MistralModelsResponse, ModelLifecycleRequest (no longer needed)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 14:42:52 +03:00
26e5e7ead8 feat: implement mistral.rs harness and neuron model API
All checks were successful
CI / Format, lint, build, test (push) Successful in 2m30s
CI / Build SRPM (push) Has been skipped
CI / Publish to COPR (push) Has been skipped
- MistralRsHarness: Harness trait impl wrapping mistral.rs HTTP API
  (list/load/unload models, health check, start/stop via systemd)
- HarnessRegistry: maps harness name -> Box<dyn Harness>, built from
  neuron.toml config
- Neuron API endpoints: GET /models, POST /models/load,
  POST /models/unload, GET /models/:id/endpoint
- NeuronConfig: figment-based config loading from neuron.toml
- Integration test: full model lifecycle through mock mistral.rs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 14:29:42 +03:00
6dc717ebcd feat: add neuron daemon with GPU discovery and health endpoints
All checks were successful
CI / Format, lint, build, test (push) Successful in 2m29s
CI / Build SRPM (push) Has been skipped
CI / Publish to COPR (push) Has been skipped
Replace cortex-agent stub with neuron (cortex-neuron binary).

cortex-core additions:
- discovery.rs: DeviceInfo, DiscoveryResponse, DeviceHealth, HealthResponse
- harness.rs: Harness async trait, HarnessConfig, ModelSpec, ModelInfo

neuron crate (crates/neuron/):
- discovery.rs: nvidia-smi CSV parsing (pure functions) + system
  discovery via uname/nvidia-smi/nvcc
- health.rs: cached GPU health polling every 5s
- api.rs: GET /discovery and GET /health axum handlers
- main.rs: CLI entrypoint with --port flag (default 9090)
- harness stubs for mistralrs (Phase 8) and llamacpp (Phase 11)

12 new tests (9 unit + 3 integration), 35 total.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 14:23:42 +03:00
0da68833af feat: scaffold cortex workspace
Rust reverse-proxy for multi-node mistral.rs inference clusters.
Includes crate structure (cortex-core, cortex-gateway, cortex-agent,
cortex-cli), config loading, OpenAI/Anthropic translation stubs,
model routing, eviction, polling, and streaming proxy scaffolding.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-14 18:13:30 +03:00