llm自托管
RT @QwenAIFans: ⚡️ DFlash2 just took Qwen3.8-27B on one 3090 from 201 to 296 tok/s.
Same INT4 prompt, greedy. Four users at once still hit ~401 tok/s total.
Caveat: author 3090 run; this engine is 3090-only so far.
via tuan3w / qwen-warp 👇
https://t.co/O9yi1ngNpj https://t.co/ld44O3Hj2z