Llama-3_1-Nemotron-Ultra-253B-v1
Support summary
Llama-3_1-Nemotron-Ultra-253B-v1 is a checkpoint published by NVIDIA, built on the DeciLMForCausalLM architecture. SGLang 0.5.19, the newest indexed SGLang release, documents support. vLLM and TensorRT-LLM list its architecture, but not this exact checkpoint.
SGLang documents support in 13 of 13 indexed releases, from 0.5.10 to 0.5.19.
- Configured context
- 131,072 tokens
- License
- nvidia-open-model-license
Hugging Face model card
- Publisher
- NVIDIA
- Task
- text generation
- License
- nvidia-open-model-license
- Library
- transformers
- Architecture
- DeciLMForCausalLM
- Weight tensor elements
- 253.4B
- Tensor types
- BF16
- Configured context
- 131,072 tokens
- Languages
- en
- Weight access
- Public
- Repository created
- 2025-04-07
Model notes and sources
- SGLang v0.5.19 · docs/docs/supported-models/generative_models.mdx · 3 indexed revisions, v0.5.17 to v0.5.19
- 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
- nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 · publisher model card
- nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 · Hugging Face metadata
- nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 · publisher configuration
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
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 | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||