f4f4b3ff26
* wip: test logic to use multiple specs * feat: introduce composite speculative decoding stages * handle MTP context and draft invalidation * fix: allow gemma mtp for speculative stages * fix: normalize spec stage keys * refactor: remove enable_mtp flag and improve speculative stage handling * fix: update cached text tokens handling for stage chains * feat: implement sync for external MTP after non-MTP accept |
||
|---|---|---|
| .. | ||
| backend | ||
| development | ||
| android.md | ||
| autoparser.md | ||
| build.md | ||
| docker.md | ||
| function-calling.md | ||
| install.md | ||
| llguidance.md | ||
| parameters.md | ||
| speculative.md | ||