# Vllm Project

> Markdown twin of https://roboterminal.app/companies/vllm-project · https://roboterminal.app/companies/vllm-project.md

## On shared sources

- [AMD](https://roboterminal.app/companies/amd) (2)
- [vLLM](https://roboterminal.app/companies/vllm) (2)
- [NVIDIA](https://roboterminal.app/companies/nvidia) (1)
- [SemiAnalysis](https://roboterminal.app/companies/semianalysis) (1)

## Pulse

- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2102050260721807397)
  Experiments have shown that offloading Engram to DRAM results in up to 50% better performance on H200, B200, B300, and even GB300 NVL72. Our technical team has collaborated with 10x engineers from @Em…
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2100948236139712988)
  Great blog from Kevin Lu at @vllm_project about quality control at the inference engine. Unfortunately, @AnushElangovan has not provided enough stable AMD QA clusters to vLLM, which leads to an order …
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2098238630015705267)
  ALERT🚨 GB300 NVL72 NVLINK BACKPLANE ENABLES 13x BETTER PERF PER DOLLAR THAN HOPPER ON AGENTIC INFERENCE Through extreme co-design, GB300 NVL72 uses an innovative copper backplane to expand the scale-…
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2097007346421531008)
  ALERT🚨: AMD INCREASED @vllm_project PERFORMANCE BY 11x IN LESS THAN 19 DAYS ON MI355X AGENTIC WORKLOADS on the modern MiniMax M3 model! This was done entirely through software optimizations, mainly b…

---

Source: Roboterminal · https://roboterminal.app/companies/vllm-project.md