medium10 pts · first answer countsmodel-servingkv-cachetooling
vLLM gpu_memory_utilization
In vLLM you set gpu_memory_utilization=0.90 on an 80 GB GPU. What does this control?
Discussion 0
Join free to post in the discussion.
Related questions
- When batch inference fitsMLOps Engineer
- Traffic before the model has loadedMLOps Engineer
- Why export a model to ONNXMLOps Engineer
- Protocol for internal inference callsMLOps Engineer
- Latency and throughputMLOps Engineer
- What TTFT measuresMLOps Engineer
- Gap between streamed tokensMLOps Engineer
- Two phases of LLM generationMLOps Engineer