hard20 pts · first answer countsmodel-servingkv-cachequantization
Errors only on very long documents
After enabling FP8 KV cache, short chats are fine but answers on 100K-token documents get worse. What is a likely reason and response?
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