Join us

ContentUpdates and recent posts about vLLM..
Link
@devopslinks shared a link, 2ย days, 11ย hours ago
FAUN.dev()

.self: A new Top-Level Domain built from theground up to support self-hosting

Operated as a public good, .self TLD will be designed and implemented according to human-centered principles to enable anyone to take full ownership of their data... read more ย 

Story
@laura_garcia shared a post, 2ย days, 18ย hours ago
Software Developer, RELIANOID

๐—ฅ๐—˜๐—Ÿ๐—œ๐—”๐—ก๐—ข๐—œ๐—— ๐—ฎ๐—น๐—ถ๐—ด๐—ป๐˜€ ๐˜„๐—ถ๐˜๐—ต ๐˜๐—ต๐—ฒ ๐—ฝ๐—ฟ๐—ถ๐—ป๐—ฐ๐—ถ๐—ฝ๐—น๐—ฒ๐˜€ ๐—ผ๐—ณ ๐—œ๐—ฆ๐—ข/๐—œ๐—˜๐—– ๐Ÿฒ๐Ÿฎ๐Ÿฐ๐Ÿฐ๐Ÿฏ

๐Ÿšจ ๐—œ๐—ป๐—ฑ๐˜‚๐˜€๐˜๐—ฟ๐—ถ๐—ฎ๐—น ๐—ฐ๐˜†๐—ฏ๐—ฒ๐—ฟ๐˜€๐—ฒ๐—ฐ๐˜‚๐—ฟ๐—ถ๐˜๐˜† ๐—ถ๐˜€ ๐—ป๐—ผ ๐—น๐—ผ๐—ป๐—ด๐—ฒ๐—ฟ ๐—ผ๐—ฝ๐˜๐—ถ๐—ผ๐—ป๐—ฎ๐—น โ€” ๐—ถ๐˜'๐˜€ ๐—ณ๐—ผ๐˜‚๐—ป๐—ฑ๐—ฎ๐˜๐—ถ๐—ผ๐—ป๐—ฎ๐—น. We're proud to share that ๐—ฅ๐—˜๐—Ÿ๐—œ๐—”๐—ก๐—ข๐—œ๐—— ๐—ฎ๐—น๐—ถ๐—ด๐—ป๐˜€ ๐˜„๐—ถ๐˜๐—ต ๐˜๐—ต๐—ฒ ๐—ฝ๐—ฟ๐—ถ๐—ป๐—ฐ๐—ถ๐—ฝ๐—น๐—ฒ๐˜€ ๐—ผ๐—ณ ๐—œ๐—ฆ๐—ข/๐—œ๐—˜๐—– ๐Ÿฒ๐Ÿฎ๐Ÿฐ๐Ÿฐ๐Ÿฏ, the ๐˜ช๐˜ฏ๐˜ต๐˜ฆ๐˜ณ๐˜ฏ๐˜ข๐˜ต๐˜ช๐˜ฐ๐˜ฏ๐˜ข๐˜ญ๐˜ญ๐˜บ ๐˜ณ๐˜ฆ๐˜ค๐˜ฐ๐˜จ๐˜ฏ๐˜ช๐˜ป๐˜ฆ๐˜ฅ ๐˜ด๐˜ต๐˜ข๐˜ฏ๐˜ฅ๐˜ข๐˜ณ๐˜ฅ ๐˜ง๐˜ฐ๐˜ณ ๐˜ด๐˜ฆ๐˜ค๐˜ถ๐˜ณ๐˜ช๐˜ฏ๐˜จ ๐˜๐˜ฏ๐˜ฅ๐˜ถ๐˜ด๐˜ต๐˜ณ๐˜ช๐˜ข๐˜ญ ๐˜ˆ๐˜ถ๐˜ต๐˜ฐ๐˜ฎ๐˜ข๐˜ต๐˜ช๐˜ฐ๐˜ฏ ๐˜ข๐˜ฏ๐˜ฅ ๐˜Š๐˜ฐ๐˜ฏ๐˜ต๐˜ณ๐˜ฐ๐˜ญ ๐˜š๐˜บ๐˜ด๐˜ต๐˜ฆ๐˜ฎ๐˜ด (๐˜๐˜ˆ๐˜Š๐˜š). From manufacturing and energy to utilities, go..

ย Activity
@david6983 started using tool Kubernetes , 3ย days, 16ย hours ago.
ย Activity
@david6983 started using tool Helm , 3ย days, 16ย hours ago.
ย Activity
@david6983 started using tool Google Kubernetes Engine (GKE) , 3ย days, 16ย hours ago.
ย Activity
@david6983 started using tool Flux , 3ย days, 16ย hours ago.
ย Activity
@david6983 started using tool Argo CD , 3ย days, 16ย hours ago.
Story
@laura_garcia shared a post, 3ย days, 18ย hours ago
Software Developer, RELIANOID

๐—ผ๐—ฝ๐—ฒ๐—ฟ๐—ฎ๐˜๐—ถ๐—ผ๐—ป๐—ฎ๐—น ๐—ฟ๐—ฒ๐˜€๐—ถ๐—น๐—ถ๐—ฒ๐—ป๐—ฐ๐—ฒ ๐—ฎ๐—ป๐—ฑ ๐˜๐—ต๐—ฒ ๐˜๐—ฟ๐˜‚๐—ฒ ๐—ฐ๐—ผ๐˜€๐˜ ๐—ผ๐—ณ ๐—ฑ๐—ผ๐˜„๐—ป๐˜๐—ถ๐—บ๐—ฒ

๐ŸŽ‰ We're honored to be featured in this excellent article on one of today's most important topics: ๐—ผ๐—ฝ๐—ฒ๐—ฟ๐—ฎ๐˜๐—ถ๐—ผ๐—ป๐—ฎ๐—น ๐—ฟ๐—ฒ๐˜€๐—ถ๐—น๐—ถ๐—ฒ๐—ป๐—ฐ๐—ฒ ๐—ฎ๐—ป๐—ฑ ๐˜๐—ต๐—ฒ ๐˜๐—ฟ๐˜‚๐—ฒ ๐—ฐ๐—ผ๐˜€๐˜ ๐—ผ๐—ณ ๐—ฑ๐—ผ๐˜„๐—ป๐˜๐—ถ๐—บ๐—ฒ. It's always rewarding to see industry experts recognize the critical role that intelligent application delivery, high availability, and resilient tr..

Article mind technology relianoid
Story Keploy Team
@sancharini shared a post, 4ย days, 11ย hours ago

Building Production-Ready Pipelines with Open Source Automation Tools: Real Patterns That Work

Learn the patterns that separate production-ready pipelines from those that fail. How experienced teams use open source automation tools effectively.

Open Source Automation Tools Modern Engineering Teams Are Building Pipelines Around
Story
@laura_garcia shared a post, 6ย days, 22ย hours ago
Software Developer, RELIANOID

Network Load Balancer

๐ŸŒ ๐˜Ž๐˜ณ๐˜ฆ๐˜ข๐˜ต ๐˜ฑ๐˜ฆ๐˜ณ๐˜ง๐˜ฐ๐˜ณ๐˜ฎ๐˜ข๐˜ฏ๐˜ค๐˜ฆ ๐˜ด๐˜ต๐˜ข๐˜ณ๐˜ต๐˜ด ๐˜ธ๐˜ช๐˜ต๐˜ฉ ๐˜ช๐˜ฏ๐˜ต๐˜ฆ๐˜ญ๐˜ญ๐˜ช๐˜จ๐˜ฆ๐˜ฏ๐˜ต ๐˜ต๐˜ณ๐˜ข๐˜ง๐˜ง๐˜ช๐˜ค ๐˜ฅ๐˜ช๐˜ด๐˜ต๐˜ณ๐˜ช๐˜ฃ๐˜ถ๐˜ต๐˜ช๐˜ฐ๐˜ฏ. A ๐—ก๐—ฒ๐˜๐˜„๐—ผ๐—ฟ๐—ธ ๐—Ÿ๐—ผ๐—ฎ๐—ฑ ๐—•๐—ฎ๐—น๐—ฎ๐—ป๐—ฐ๐—ฒ๐—ฟ helps organizations maximize availability, eliminate bottlenecks, and keep critical applications running smoothlyโ€”even under heavy traffic or unexpected failures. In our latest article, we explain how Layer 4 l..

vLLM is an advanced open-source framework for serving and running large language models efficiently at scale. Developed by researchers and engineers from UC Berkeley and adopted widely across the AI industry, vLLM focuses on optimizing inference performance through its innovative PagedAttention mechanism โ€” a memory management system that enables near-zero waste in GPU memory utilization. It supports model parallelism, continuous batching, tensor parallelism, and dynamic batching across GPUs, making it ideal for real-world deployment of foundation models. vLLM integrates seamlessly with Hugging Face Transformers, OpenAI-compatible APIs, and popular orchestration tools like Ray Serve and Kubernetes. Its design allows developers and enterprises to host LLMs with reduced latency, lower hardware costs, and increased throughput, powering everything from chatbots to enterprise-scale AI services.