Inference on 时影https://huggingaha.github.io/tags/inference/Recent content in Inference on 时影Hugo -- gohugo.iozh-cnhuggingaha@gmail.com (时影)huggingaha@gmail.com (时影)© 2026 时影Sun, 14 Sep 2025 00:00:00 +0000击败 LLM 推理中的非确定性https://huggingaha.github.io/posts/defeating-nondeterminism-in-llm-inference/Sun, 14 Sep 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/posts/defeating-nondeterminism-in-llm-inference/REFRAG：Rethinking RAG based Decodinghttps://huggingaha.github.io/posts/refrag/Fri, 12 Sep 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/posts/refrag/