Tianyi Cui· @tianyi · X·· 1 小时前同事件AI 评分67
AI 导读
DeepSeek 开源高性能大规模推理框架 DeepInfer，采用 Apache-2.0 许可，仓库地址 https://github.com/deepseek-ai/DeepInfer。支持优化 kernel、模型与 sampler 运行时，Attention DP、平衡 CP、MoE EP + EPLB 等并行方案，以及 DSpark、置信度调度验证、SWA bounded replay、零开销异步批量调度、batch-invariant 推理、确定性采样和结构化输出。
同一件事，精选收录的是《DeepSeek 全面开源内部推理框架 DeepInfer》
正文 · 原文
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