# DeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85%

_Friday, July 17, 2026 at 8:00 AM EDT · AI · Latest · Tier 2 — Notable_

![DeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85% — Primary](https://images.ctfassets.net/jdtwqhzvc2n1/1LKLzOBxewK4b4E04bGEIY/be7d3b2bd4874c5b8a3001b8498b5e02/ChatGPT_Image_Jun_29__2026__04_35_22_PM.png?w=800&q=75)

Chinese AI firm DeepSeek said over the weekend it released DSpark, a new MIT-licensed framework designed to accelerate large language model inference by up to 85 percent without altering model outputs. The system uses a speculative decoding approach in which a lighter draft component proposes likely next tokens for a larger target model to verify in parallel, allowing the model to advance multiple tokens at once when guesses are correct. DeepSeek published a technical paper, model checkpoints and DeepSpec, a codebase for training and evaluating speculative decoding systems, on its public GitHub and Hugging Face pages. The company applied DSpark to its latest open models, DeepSeek-V4-Flash and DeepSeek-V4-Pro, and said the method also works with other open-weight families such as Alibaba's Qwen and Google's Gemma. In production tests, DeepSeek reported per-user generation speedups of 60 percent to 85 percent for V4-Flash and 57 percent to 78 percent for V4-Pro over its prior MTP-1 baseline at matched system capacity. Aggregate throughput improvements reached 51 percent for V4-Flash and 52 percent for V4-Pro at defined service targets. The release aims to address the high cost of serving large models quickly enough for real-time applications.

## Sources

- [VentureBeat](https://venturebeat.com/orchestration/deepseek-open-sources-dspark-a-new-framework-to-speed-up-llm-inference-by-up-to-85)

---
Canonical: https://techandbusiness.org/newswire/1y9fEn24wTIZYBpEZDTwtC
Retrieved: 2026-07-17T14:45:35.096Z
Publisher: Tech & Business (techandbusiness.org)