LMDeploy
PulseAugur coverage of LMDeploy — every cluster mentioning LMDeploy across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
vLLM serving engine releases new minor versions every 13 days, increasing upgrade risks
The LLM serving engine vLLM has a rapid release cadence, averaging a new minor series every 13.5 days over a recent 365-day period. This frequent updating, however, comes with a significant number of breaking changes, w…
-
FOCUS system boosts DLLM inference speed by 3.5x
Researchers have developed a new inference system called FOCUS designed to improve the efficiency of Diffusion Large Language Models (DLLMs). This system addresses the high decoding costs associated with DLLMs by dynami…
-
AI model serving vulnerability exploited within 13 hours of LMDeploy disclosure
A critical vulnerability in LMDeploy, an AI model serving tool, was exploited within 13 hours of its disclosure. This rapid exploitation highlights the significant attack surface presented by AI model serving infrastruc…