local-llm-autotune
github.com/tanavc1/local-llm-autotune
37f50f2mainsynced 2h ago
Code HealthView report
Average health
5.7/10
Fair
Hotspot health
2.9/10
Critical
CostsView costs →
What this repo's indexing and doc generation cost, per sync.
Open the Costs page →Attention Needed23
autotune/api/backends/chain.pyUngoverned Hotspot
High-churn file with no governing decision
Formula/llm-autotune.rbKnowledge Silo
100% single-owner concentration
LlmAutotuneDead Code
Safe to delete (179 lines)
autotune/api/chat.pyUngoverned Hotspot
High-churn file with no governing decision
autotune/init.pyKnowledge Silo
100% single-owner concentration
No commit history
Commit activity appears once git history is indexed.
Recent DecisionsView all
Measure unified memory via Ollama /api/ps rather than psutilproposed
2h ago · commentDynamically size num_ctx to needed request tokensproposed
2h ago · commentModel fitness assessment: SWAP_RISK downgraded to warningproposed
2h ago · changelogRecommendation output no longer uses pagerproposed
2h ago · changelogBackend priority: Ollama listed firstproposed
2h ago · changelogEliminate MLX as default torch import pathproposed
2h ago · changelogTop Hotspots5 of 12View all
Commit Activity
Feature Fix Refactor Dependency