Lap Tran
dd2726c0dd
CI / build (push) Has been cancelled
7 memory files covering: - audit-bug-patterns: recurring status.py bug patterns - vram-model-matching: three-tier model prefix matching - dashboard-security: .state priority, CORS removal, register-guards - state-machine-workflow: legal transitions and approval gates - testing-conventions: pytest patterns and helpers - audit-process: report conventions and batch processing - framework-architecture: enforcement layers and key files
656 B
656 B
vram_detect.py model prefix matching
_lookup_model_context() must avoid false prefix matches. The correct approach is three-tier:
- Exact match —
name_lower == key_lower - Ollama parameter tag —
name_lower.startswith(key_lower + ":")(e.g.deepseek-r1:7bmatchesdeepseek-r1) - Known instruction-tuning suffix —
name_lower.startswith(key_lower + "-")only if next segment is in_KNOWN_MODEL_SUFFIXES = {"instruct", "chat", "it", "fp16", "f16", "bf16"}
Keys sorted by length descending so most specific match wins first. This prevents phi-4 matching phi-4-mini-instruct or gpt-4o matching gpt-4o-foo-unknown.