AlexBrandes/cmp170hx-qwen38-flash-next
Qwen3.8-Flash-Next (W4A16) on 2x NVIDIA CMP 170HX with vLLM pipeline parallel: 226 tok/s single-user, 840 tok/s at 8 users, 262K context, HumanEval 157/164
GitHub repository with 12 stars and 2 forks.
Language: Shell
Topics: cmp-170hx, llm-inference, qwen, sm80, vllm