The sm_120 shared-memory cliff: why FP8 KV cache crashes vLLM on workstation Blackwell

If you run vLLM with --kv-cache-dtype fp8 on a DeepSeek-family (MLA) model and your GPU is a GB10, an RTX PRO 6000, or any workstation or consumer Blackwell card, there is a decent chance the engine dies on startup with: triton. runtime. errors.

Source: [Dev.to](https://dev.to/conatusai/the-sm120-shared-memory-cliff-why-fp8-kv-cache-crashes-vllm-on-workstation-blackwell-1dji)