From Ollama to vLLM
From 24GB Blackwell workstation cards to one 128GB DGX Spark, then two Sparks and a QSFP cable: running DeepSeek-V4-Flash-Vision-Exp locally, understanding vLLM, and planning the next step with a 200Gb/s switch.
Thoughts on technology, infrastructure, and AI
Viewing posts tagged deepseek Clear filter
2 posts found
From 24GB Blackwell workstation cards to one 128GB DGX Spark, then two Sparks and a QSFP cable: running DeepSeek-V4-Flash-Vision-Exp locally, understanding vLLM, and planning the next step with a 200Gb/s switch.
Pangolin 1.22 shipped an AI Gateway this week. The provider list covers OpenAI, Anthropic and Gemini, but there's no Kimi or DeepSeek button. Here's how to register both as custom providers, and why the missing buttons turn out not to matter.