nicole pardal e082d60a24 truncation: fixed runner truncation logic + removed server truncation (#12839) ... This PR consolidates all embedding prompt-length checking, truncation, and prompt token counting into the runner to ensure a single source of truth.		2025-12-08 11:20:28 -08:00
..
cache.go	feat(model): add qwen3vl (#12665)	2025-10-28 17:39:47 -07:00
cache_test.go	feat(model): add qwen3vl (#12665)	2025-10-28 17:39:47 -07:00
multimodal.go	ggml: Enable op_offload to improve partial offload performance	2025-10-30 13:53:10 -07:00
runner.go	truncation: fixed runner truncation logic + removed server truncation (#12839)	2025-12-08 11:20:28 -08:00