Evan Reichard 328bb6e1db feat(llama-swap): add ik-llama-cpp package and Qwen3.6-27B MTP config ...

Add ikawrakow/ik_llama.cpp as a new package with CUDA/Vulkan support,
enabling MTP (Multi-Token Prediction) and IQ4_KS quantization. Wire it
into llama-swap with a new 'ik-qwen3.6-27b-iq4ks-thinking' model config
and 'iq36' alias. Also add a chat template download to the vLLM setup
script and include the binary on lin-va-desktop.

2026-05-12 16:19:34 -04:00

2.7 KiB

Executable File

Raw Blame History

View Raw