Commit Graph

8 Commits

Author SHA1 Message Date
Keysat e783653ef0 v0.23.0:0 - local / fine-tuned model support
Add models that live as a directory on a Spark (e.g. LoRA-merged fine-tunes),
not just Hugging Face repos.

- ModelDef gains local_path; a model must set exactly one of repo / local_path.
  The validator also enforces the local-path whitelist and that any
  --chat-template lives inside local_path (only that dir is mounted).
- build_launch_command bind-mounts the dir into the vLLM container at the SAME
  host==container path via the launch script's VLLM_SPARK_EXTRA_DOCKER_ARGS hook,
  then `vllm serve <dir>`. No launch-cluster.sh change (verified the upstream
  expands that var unquoted; contract noted in runbook.md).
- shellsafe.validate_local_path: absolute path, charset whitelist, no '.'/'..'.
- POST /api/models validates the full entry via ModelDef before persisting, so a
  bad entry can't be written and then break catalog load; _merge_overrides skips
  an invalid override entry instead of failing the whole catalog.
- disk.py size-probes a local path with du; disk-delete refused for local models.
- UI: "+ Add local model" dialog, `local` badge, path shown instead of an HF
  link, delete button hidden for local models.
- Tests: local launch + injection round-trip, chat-template location, traversal,
  exactly-one-source, _merge_overrides skip-invalid (94 pass). Reviewer-agent
  pass; findings addressed.
2026-06-17 22:27:41 -05:00
Keysat c179389731 docs: trim Current state post-matrix-bridge ship; add bot-tile ops note to runbook 2026-06-15 23:18:28 -05:00
Keysat 98988057a2 v0.18.0:1 - scrub owner-specific hostnames, ips, usernames, names from tracked files
Replace real cluster IPs/hosts/usernames and example names with neutral
placeholders across docs, ops notes, package install text, and the offline
redaction test; delete the obsolete build-time starter prompt. Closes the
portability audit's single blocker. No runtime behavior change.
2026-06-12 15:07:34 -05:00
Keysat 8d839e3714 v0.13.0:4 - redaction gateway, embeddings proxy, expanded audio API
- Add redaction gateway (redaction_gateway.py, redaction/ scrub + tests)
- Add embeddings proxy and spark_embed service (Dockerfile + main.py)
- Expand audio_proxy with speaker-aware handling; deep_health/health/server updates
- Package: configureSparks action + sparkConfig model updates, manifest/main wiring
- Docs: AUDIO_API, EMBEDDINGS, REDACTION_GATEWAY; HANDOFF and runbook/known-issues refresh
2026-06-11 17:45:57 -05:00
Grant 87334f85f0 Add per-model descriptions + repo-cleanup polish
- models.yaml: add 'description' field for all 5 models (generic, anyone-can-use)
- ModelDef gains optional description: str | None field
- UI: render description below meta tags; mute the repo line further
- escapeHtml() for safety in case descriptions/names contain HTML chars
- Update runbook: how to add a new model with description
2026-05-12 10:19:09 -05:00
Grant 34bdbb7aba Add Spark prerequisites section to runbook (spark-vllm-docker is upstream + Spark-side) 2026-05-12 10:05:17 -05:00
Grant 342e150266 Add safe optimization flags to gemma4 + qwen36 (fastsafetensors, prefix-caching, fp8 kv)
Aligned with sibling recipes in eugr/spark-vllm-docker. Applies on next swap to each model.
First real swap gemma4 -> qwen36 succeeded in 5:30 with --moe_backend=flashinfer_cutlass.
2026-05-12 09:49:08 -05:00
Grant ae8efa1754 Initial scaffold: image/ FastAPI app, models.yaml, docs
- image/ FastAPI app: /api/status, /api/swap, /api/swap/{id}/stream, /api/test-connection
- models.yaml: 5-model catalog (qwen3-vl, gemma4, qwen36, qwen3-235b-fp8, qwen25-72b)
- README, runbook, known-issues
- Dry-run swap verified against live Spark 1 (gemma4 currently loaded)
2026-05-12 09:29:13 -05:00