Wësche
@WescheNex1q
Day time artist and night time AI enthusiast. Building & benchmarking frontier LLMs on 4x DGX Spark clusters + Mac. Creator of Vesica Studio. Houston
가입 January 2013
637 팔로잉 중 2.4K 팬
One DGX Spark. Qwen3.6-35B
64 users. 700+ tok/s. 32,768 tokens in 54 seconds.
38W
Each user has their own prompt and their own KV cache, and vLLM batches every active stream through the GPU each step.
Recipe → @NVIDIAAI
더 보기
