deepseek-ai/DeepInfer

站内导读

中文 DeepInfer 是支撑 DeepSeek 大规模线上服务的高性能推理框架，本次开源版本提供离线推理能力，目前支持 DeepSeek-V4.1-Flash。它面向批量部署场景，包含优化 kernel、Attention DP 与 MoE EP 并行、DSpark 验证、异步调度、batch-invariant 推理、确定性采样和结构化输出，可运行在 NVIDIA SM100 与昇腾 950 上。适合需要复现生产级推理配置的工程团队。

README · 详细文档

来源 · 查看原文

DeepInfer

DeepInfer is the high-performance inference framework that powers DeepSeek's large-scale production services. This open-source release provides offline inference with the core features needed for serving at scale.

Supported models:

DeepSeek-V4.1-Flash

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 outputs

<details> <summary>Feature details and configuration</summary>

Optimized kernels: FlashMLA, DeepGEMM, DeepEP, TileKernels, DeepSelect, and custom TileLang kernels.
DSpark and confidence-scheduled verification: accelerate decoding with draft tokens and use confidence estimates to schedule verification. Set DEEPINFER_ENABLE_MTP_VARLEN=1; DEEPINFER_USE_NEXTN_DECODE controls the maximum draft length (default: 5).
Decoder SWA bounded replay: reduce decoder prefill work by replaying only a bounded suffix. Set DEEPINFER_YOCO_PREFILL_TRUNCATION_MODE=compact and DEEPINFER_YOCO_PREFILL_KEEP_TOKENS=140 for the default V4.1 settings; the retained suffix must cover the SWA window plus the maximum backtracking length.
Asynchronous scheduling: overlap CPU batch scheduling with device execution. Enabled by default.
Batch-invariant inference: keep model results identical across different batch compositions. Enable with DEEPINFER_BATCH_INVARIANT=1 (NVIDIA only).
Deterministic sampling: produce identical outputs for identical input tokens and sampling parameters. Set DEEPINFER_BATCH_INVARIANT=1 DEEPINFER_ENABLE_MTP_VARLEN=0 and pass a fixed seq_seed to SamplingParams (NVIDIA only).
Structured outputs: constrain generation to a regex, JSON schema, or EBNF grammar. Pass so_args={"schema_type": ..., "schema": ...} to SamplingParams; see examples.

</details>

Supported hardware:

NVIDIA SM100 GPUs
Huawei Ascend 950 NPUs

Required for a complete inference service (not included in this release):

A KV cache system
VE/Prefill/Decode disaggregation (most required engine functionality is already implemented)
Load balancing across data-parallel replicas for both prefill and decode

Getting started

Prerequisites

Linux
GCC >= 13.0
Python 3.12
CUDA 13 (NVIDIA only)
CANN 9.2 (Ascend only)

Build from source

Before building DeepInfer, please create and activate an empty Python 3.12 environment.

# Use `ascend` instead for the Ascend platform
# Keep it exported in the environment where you run DeepInfer
export DEEPINFER_ACCELERATOR=nvidia
./build.sh

Offline inference

The default checkpoint, 0, is downloaded into the Hugging Face cache on the first run; set DEEPINFER_HF_MODEL_DIR=/path/to/DeepSeek-V4.1-Flash-1017 to run from a local copy instead.

python examples/offline_inference.py

See examples for details.

Performance benchmarks

Measured on 4 SM100 GPUs for prefill and 64 for decode — each within one scale-up domain. To reproduce the benchmarks, see run_sweep.sh.

Evaluation benchmarks

See eval/README.md.

License

DeepInfer is released under the Apache License 2.0. See LICENSE for details.

Acknowledgments

DeepInfer was originally built primarily on vLLM, with additional inspiration from SGLang and TensorRT-LLM. We thank their developers.

Citation

@misc{deepinfer2026,
  title = {DeepInfer: High-performance, large-scale inference framework for DeepSeek models},
  author = {DeepSeek-AI},
  year = {2026},
  publisher = {GitHub},
  howpublished = {\url{https://github.com/deepseek-ai/DeepInfer}},
}