shawnw3i/Qwen3.6-27B-AWQ-MTP

Highlights

• AWQ Marlin kernel supported (auto-converted by vLLM at runtime)
• MTP speculative decoding supported out of the box
• 110+ tok/s on a single A800 80GB (vLLM 0.21.0, MTP enabled, fp8 KV cache)

vLLM

vllm serve shawnw3i/Qwen3.6-27B-AWQ-MTP \
  --max-model-len 65536 \
  --reasoning-parser qwen3 \
  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'