AI 导读
DeepSeek 在 Apache-2.0 协议下开源高性能大规模推理框架 DeepInfer，代码位于 https://github.com/deepseek-ai/DeepInfer。支持优化 kernel 与 sampler 运行时、Attention DP/均衡 CP、MoE EP + EPLB、零开销异步批调度、批不变推理、确定性采样与结构化输出等特性。
正文
DeepSeek just open sourced its high-performance, large-scale inference framework DeepInfer in Apache-2.0 license.
https://github.com/deepseek-ai/DeepInfer
Supported features:
- Optimized kernels, model and sampler runtime
- Parallelism: Attention DP / balanced CP, MoE EP + EPLB
- DSpark and confidence-scheduled verification
- SWA bounded replay
- Asynchronous scheduling (zero-overhead batch scheduler)
- Batch-invariant inference
- Deterministic sampling
- Structured output
来源：Tianyi Cui · x.com