DeepSeek-R1
Support summary
DeepSeek-R1 is a checkpoint published by DeepSeek, built on the DeepseekV3ForCausalLM architecture. The newest indexed releases vLLM 0.28.0, SGLang 0.5.19, and TensorRT-LLM 1.2.1 all document support.
vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0. SGLang documents support in 13 of 13 indexed releases, from 0.5.10 to 0.5.19. TensorRT-LLM documents support in 2 of 2 indexed releases, from 1.2.0 to 1.2.1.
- Documented hardware
- NVIDIA / CUDA and AMD / ROCm
- Documented quantization
- FP8
- Documented features
- Reasoning parsers and 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
- Weight access
- Public
- Repository created
- 2025-01-20
Model notes and sources
Reasoning-model support does not imply arbitrary draft-model or quantization compatibility. TensorRT-LLM documents this exact checkpoint in its tagged serving example, with GPU and model-format requirements.
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- SGLang v0.5.19 · docs/docs/supported-models/generative_models.mdx · 3 indexed revisions, v0.5.17 to v0.5.19
- deepseek-ai/DeepSeek-R1 publisher metadata
- TensorRT-LLM v1.2.1 · DeepSeek-R1 serving example · 2 indexed revisions, v1.2.0 to v1.2.1
- SGLang v0.5.16 · docs_new/docs/supported-models/generative_models.mdx · 8 indexed revisions, v0.5.11 to v0.5.16
- SGLang v0.5.15.post1 · docs/supported_models/text_generation/generative_models.md · 9 indexed revisions, v0.5.10 to v0.5.15.post1
- deepseek-ai/DeepSeek-R1 · publisher model card
- deepseek-ai/DeepSeek-R1 · Hugging Face metadata
- deepseek-ai/DeepSeek-R1 · publisher configuration
- vllm · models/deepseek-ai/DeepSeek-R1.yaml
- sglang · docs/cookbook/autoregressive/DeepSeek/DeepSeek-R1.mdx
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed | 0.28.0This release | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | Checkpoint evidenceSource: SGLang v0.5.19 · docs/docs/supported-models/generative_models.mdxReviewed | 0.5.19This release | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Checkpoint evidenceSource: TensorRT-LLM v1.2.1 · DeepSeek-R1 serving exampleReviewed | 1.2.1This release | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||