Inference EngineeringAcademy
HomeFoundations Free
Courses
Pricing
Resources
JobsCoding practiceStart learning

DeepSeek-V4-Pro-DSpark

Checkpointdeepseek-ai/DeepSeek-V4-Pro-DSparkModel card indexedModel card

Support summary

DeepSeek-V4-Pro-DSpark is a checkpoint published by DeepSeek, built on the DeepseekV4ForCausalLM architecture. Official recipes or cookbooks cover vLLM, without pinning a stable release.

Documented quantization
FP8
Configured context
1,048,576 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
DeepseekV4ForCausalLM
Weight tensor elements
1.7T
Tensor types
BF16, I64, F32, F8_E4M3, I8
Quantization
fp8
Configured context
1,048,576 tokens
Weight access
Public
Repository created
2026-06-27
Source 1: deepseek-ai/DeepSeek-V4-Pro-DSpark · publisher model cardSource 2: deepseek-ai/DeepSeek-V4-Pro-DSpark · Hugging Face metadataSource 3: deepseek-ai/DeepSeek-V4-Pro-DSpark · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for DeepSeek-V4-Pro-DSpark
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLMVersion not pinnedRecipe / cookbookDocumented recipe

Official recipe

Source: vllm · models/deepseek-ai/DeepSeek-V4-Pro.yamlReviewed 		No supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLang0.5.19Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1

Recipes and cookbooks