https://yuyiao.dev/blog/determinism-in-llm-generation/2026-10-13T00:00:00+00:00https://yuyiao.dev/2026-10-21T00:00:00+00:00https://yuyiao.dev/blog/2026-10-21T00:00:00+00:00https://yuyiao.dev/blog/policy-gradient-from-objective-to-code/2026-09-22T00:00:00+00:00https://yuyiao.dev/blog/post-training-kl/2026-10-02T00:00:00+00:00https://yuyiao.dev/blog/asyncio-in-python/2026-10-21T00:00:00+00:00https://yuyiao.dev/blog/cross-entropy/2026-10-02T00:00:00+00:00https://yuyiao.dev/blog/decision-tree/2025-09-08T00:00:00+00:00https://yuyiao.dev/blog/vllm-quantization/2025-01-18T00:00:00+00:00https://yuyiao.dev/blog/vllm-swap-policy/2024-04-17T00:00:00+00:00https://yuyiao.dev/blog/linear-regression/2024-01-30T00:00:00+00:00https://yuyiao.dev/about/https://yuyiao.dev/categories/https://yuyiao.dev/tags/