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

DSpark can make decoding faster, but acceptance quality still determines how much speed the system actually realizes.
Tech Times

DeepSeek Releases DSpark: Speculative Decoding Makes V4 Up to 85 Percent Faster

DeepSeek speculative decoding framework DSpark went live June 27 on V4-Flash and V4-Pro, reporting up to 85 percent faster ...
techtimes

GLM-5.2 Open Weights Live: Top Coding Benchmark, but API Use Carries China Data Risk

a mobile phone's screen showing the logo of Chinese AI Zhipu in Beijing on January 21, 2026. Investor confidence in Chinese AI startups is riding high, but obstacles to their long-term success range ...

Z.ai’s open-weights GLM-5.2 beats GPT-5.5 on multiple long-horizon coding benchmarks for ...

It allows engineering teams to host frontier-level AI on their own sovereign infrastructure, entirely eliminating vendor lock ...
the-decoder

Zhipu AI's GLM-5.2 closes in on closed-source leaders in coding marathons

Chinese AI lab Zhipu AI releases GLM-5.2 with a stable 1-million-token context under the MIT license. On hours-long coding tasks, the open-source model trails Anthropic's Opus models by just a few ...
GitHub

TileRT: Tile-Based Runtime for

🎉 2026-02-14 · v0.1.3 Released. The v0.1.3 release introduces full support for the latest GLM-5 model, achieving up to 500 tokens/s on GLM-5-FP8 and up to 600 tokens/s on DeepSeek-V3.2. TileRT is a ...
IEEE

Wavelet-Based Deep Auto Encoder-Decoder (WDAED)-Based Image Compression

Abstract: In this work, we propose a Wavelet-based Deep Auto Encoder-Decoder Network (WDAED) based image compression which takes care of the various frequency components present in an image.