DeepSeek-V2-Lite

Checkpointdeepseek-ai/DeepSeek-V2-LiteModel card indexedModel card

Support summary

DeepSeek-V2-Lite is a checkpoint published by DeepSeek, built on the DeepseekV2ForCausalLM architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support.

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

Documented hardware: Intel GPU / XPU
Configured context: 163,840 tokens
License: deepseek

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: deepseek
Library: transformers
Architecture: DeepseekV2ForCausalLM
Weight tensor elements: 15.7B
Tensor types: BF16
Configured context: 163,840 tokens
Weight access: Public
Repository created: 2024-05-15

Source 1 Source 2 Source 3Reviewed 2026-09-05

Model notes and sources

vLLM v0.28.0 · docs/models/hardware_supported_models/xpu.md · 20 indexed revisions, v0.17.0 to v0.28.0
deepseek-ai/DeepSeek-V2-Lite · publisher model card
deepseek-ai/DeepSeek-V2-Lite · Hugging Face metadata
deepseek-ai/DeepSeek-V2-Lite · publisher configuration
Reviewed 2026-09-05

Engine support

3 engines

Engine support for DeepSeek-V2-Lite
Engine	Release	Evidence scope	Last known supported
vLLM	`0.28.0`Newest indexed	Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/hardware_supported_models/xpu.mdReviewed 2026-09-05	`0.28.0`This release
Features, dependencies and evidence for vLLM 0.28.0
SGLang	`0.5.19`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM	`1.2.1`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1