Expired50% confidenceBenchmarkExact time
In the DeepSeek V4 (D300 machine) test scenario with 8K input/1K output, DSpark achieves a single-user token rate improvement of nearly 150x compared to the baseline.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/9/2026(expired)
Sources
DeepSeek投机解码算法正式合并vLLM主干，单用户速率提升显著
bilibili小工蚁创始人7/7/2026
Related Claims
UnverifiedIn the STM32 embedded development test, the locally deployed DS4 model had an average output speed of approximately 23 tokens/second, memory usage spiked to 110 GB during inference, and the peak speed reached 83.8 tokens/second.71% similarUnverifiedSafeTensors支持内存映射（mmap），加载速度比pickle格式快数倍64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/485975API
curl https://kongchang.com/api/v1/knowledge/claims/485975MCP
get_claim(id=485975)