haylanandClaude Bot 17747694bd feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier ...

Replace MTP with draft-dflash and a separate DFlash2 drafter GGUF.
Remove the qwen-classifier backend to free VRAM (GPU was at 100%).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

2026-10-05 21:28:55 +02:00

..

claude-code.md

docs: restructure around source-of-truth pages

2026-09-24 21:51:01 +02:00

index.md

feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier

2026-10-05 21:28:55 +02:00

kimi-cli.md

docs: restructure around source-of-truth pages

2026-09-24 21:51:01 +02:00

opencode.md

chore(config): revisteded ai configuration for opencode

2026-10-02 06:53:33 +00:00

qwen-code.md

feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier

2026-10-05 21:28:55 +02:00