docs(lemonade): ADR-0008/0009/0010 + adoption plan + spike #2 + grill outputs#154
Merged
Merged
Conversation
… outputs
Post-grill source of truth for v0.2 Lemonade migration. Supersedes
ADR-0006 + ADR-0007; locks the 22-PR implementation sequence.
- ADR-0008: Lemonade adoption as unified inference runtime (Path 4).
Rescinds ADR-0007's preload validation (per-type LRU + nuclear-evict
exemption list make it unnecessary). Locks --threads N mandatory.
- ADR-0009: FLM trio NPU packing (chat + asr + embed in one AMDXDNA HW
context via --asr 1 --embed 1).
- ADR-0010: bundle picker first-run UX (no default stack).
- ADR-0006/0007: Status -> Superseded by ADR-0008.
- CONTEXT.md: glossary additions from grill (slot type, group, FLM trio,
bundle tiers, model namespace, fresh install, v0.1.x -> v0.2 upgrade).
- lemonade-adoption-plan-2026-05-22.md: 13 sections, 22-PR roadmap,
service topology, slot model, NPU+FLM trio, model layout, OmniRouter
spec, bundle picker, v0.1.x->v0.2 clean break, slot architecture
migration, implementation sequence, operational caveats.
- lemonade-spike-2-findings + runbook: empirical Phase A/B/C results,
/diagnose chain that uncovered --threads deadlock, FLM trio
verification.
- lemonade-research-2026-05-22/{researcher,architect,api,ui}.md:
4-agent design pass with deep code references.
Implementation contract: docs/internal/lemonade-adoption-plan-2026-05-22.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Post-grill source of truth for v0.2 Lemonade migration. Supersedes ADR-0006 + ADR-0007; locks the 22-PR implementation sequence.
Nothing here ships code — pure docs PR. Lands the contract before PRs 3–22.
Key documents
0008-lemonade-adoption.md) — Lemonade as unified runtime (Path 4). Single `lemond` per host, all modalities via Lemonade, per-type LRU concurrency, mandatory `--threads N`, FLM trio for NPU, OmniRouter client-side, no `extra.*` namespace, no v0.1.x migration. §3 explicitly rescinds ADR-0007's preload validation — per-type LRU + nuclear-evict's not-found exemption list reduce the original hazard.Heads-up — parallel-session collision
PRs #143 (SlotConfig.device + schema_v2) and #144 (preload validation + idle-unload, refs ADR-0007) landed on `main` before this doc PR was visible. ADR-0008 §3 specifically removes the preload validation work that #144 implements. Decision on whether to revert / scope-down / keep-defensively will be raised in a follow-up PR or issue once this docs PR lands.
Test plan
🤖 Generated with Claude Code