mirror of
https://github.com/ollama/ollama.git
synced 2026-10-21 11:01:33 +00:00
505e35f2b9
The heuristic schedule grew the draft toward a fixed cap on acceptance alone, maximizing accepted-tokens-per-step rather than throughput, and on a steep-forward target it regressed below no speculation. Replace it with an engine-level controller that drafts the depth maximizing committed-tokens-per-wallclock from live per-position acceptance and persisted per-width forward cost, with no draft-length cap; the heuristic schedule and the OLLAMA_MLX_MTP_* env vars go with it. |
||
|---|---|---|
| .. | ||
| cohere2_moe | ||
| gemma3 | ||
| gemma4 | ||
| glm4_moe_lite | ||
| laguna | ||
| llama | ||
| nn | ||
| qwen3 | ||
| qwen3_5 | ||
| qwen3_5_moe | ||