DeepSeek-V3.1

Checkpointdeepseek-ai/DeepSeek-V3.1Model card indexedModel card

Support summary

DeepSeek-V3.1 is a checkpoint published by DeepSeek, built on the DeepseekV3ForCausalLM architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. Official recipes or cookbooks cover SGLang, without pinning a stable release. TensorRT-LLM lists its architecture, but not this exact checkpoint.

vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.

Documented hardware
NVIDIA / CUDA and AMD / ROCm
Documented quantization
FP8
Documented features
Tensor parallelism
Configured context
163,840 tokens
License
mit

Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.

Hugging Face model card
Publisher
DeepSeek
Task
text generation
License
mit
Library
transformers
Architecture
DeepseekV3ForCausalLM
Weight tensor elements
684.5B
Tensor types
BF16, F8_E4M3, F32
Quantization
fp8
Configured context
163,840 tokens
Base models
deepseek-ai/DeepSeek-V3.1-Base
Weight access
Public
Repository created
2025-08-21
Source 1: deepseek-ai/DeepSeek-V3.1 · publisher model cardSource 2: deepseek-ai/DeepSeek-V3.1 · Hugging Face metadataSource 3: deepseek-ai/DeepSeek-V3.1 · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for DeepSeek-V3.1
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedCheckpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed 0.28.0This release
Features, dependencies and evidence for vLLM 0.28.0
SGLangVersion not pinnedRecipe / cookbookDocumented recipe

Official recipe

Source 1: sglang · docs/cookbook/autoregressive/DeepSeek/DeepSeek-V3_1.mdxSource 2: sglang · docs/src/snippets/autoregressive/deepseek-v31-deployment.jsxReviewed
No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedArchitecture listed; exact checkpoint unknownNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1

Recipes and cookbooks