#DSpark

8 related articles

Jul 25, 2026·2 min

DSpark: DeepSeek Partners with Peking University to Open-Source Inference Acceleration, Boosting Speed by Up to 85%

DeepSeek partners with Peking University to open-source DSpark, an inference acceleration tech boosting single-user speed by 57%-85% under high concurrency. Learn its three core designs and the DSpec framework.

Jul 25, 2026·2 min

DSpark: DeepSeek and Peking University Open-Source Inference Acceleration Tech with Up to 85% Speed Boost

DeepSeek and Peking University open-source DSpark, an inference acceleration tech boosting single-user generation speed by 57%-85% under high concurrency. Learn its 3 core designs and the DSpec framework.

Jul 17, 2026·4 min

DSpark Open Source: DeepSeek's Inference Acceleration Tech That Doubles LLM Speed

DeepSeek and Peking University open-source DSpark, an inference acceleration technology using semi-autoregressive architecture and dynamic scheduling to boost LLM speed by 50%+ and double GPU concurrency without quality loss.

Jul 16, 2026·3 min

DeepSeek Open-Sources DSpark: 50%–400% LLM Inference Speedup Without Retraining

DeepSeek open-sources DSpark, delivering 50%–400% LLM inference speedup with no retraining or quantization, via semi-autoregressive drafting and confidence-scheduled verification.

Jul 12, 2026·2 min

SGLang Integrates DSpark: How Confidence-Driven Speculative Decoding Cracks the High-Concurrency Failure Problem

SGLang officially integrates DSpark, solving the core pain point of speculative decoding failure under high-concurrency batches via confidence-driven variable-length verification. Supports Qwen3 and DeepSeek-V4, hitting 383.7 tok/s on B300.

Jul 16, 2026·3 min

GPUStack in Action: Complete Guide to Day 0 Deployment of DeepSeek-V4-Flash

Deploy DeepSeek-V4-Flash DSpark on 8× H20-141G using GPUStack's SGLang backend on Day 0. Full walkthrough of Web UI config, parameter tuning, and 200 tokens/sec benchmark results.

Jul 11, 2026·2 min

DeepSeek Speculative Decoding Algorithm Merged into vLLM Main Branch — Single-User Token Speed Jumps Dramatically

DeepSeek's speculative decoding algorithm (DSpark) is now merged into vLLM main branch, natively supporting Qwen3 and Gemma. Tests show ~150× single-user token speed gains and ~40–50% throughput improvement.

Jul 9, 2026·4 min

AI Weekly: GPT-5.6 Launches in Three Tiers, Open-Source Inference Frameworks and Robot Safety Break Through Across the Board

This week in AI: OpenAI launches GPT-5.6 in three tiers (Sol/Terra/Luna) hitting 91.9% on coding benchmarks; DeepSeek and PKU open-source DSpark for 85% faster inference; Prime Intellect trains trillion-param models on just 28 H200s; Anthropic Claude enters Slack.