Back Original

DeepInfer: High-performance inference framework for DeepSeek models

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
Feature details and configuration
  • 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.

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

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

The default checkpoint, deepseek-ai/DeepSeek-V4.1-Flash-1017, 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.

Prefill Decode
Prefill: non-cached input throughput vs. latency Decode: output throughput vs. per-user speed

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.

See eval/README.md.

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

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

@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}},
}