Tan TJian

[Tan TJian @Rxday000]

@mgoin_ @mgoin We should have more of the food trip 😋 let me know when you are in Asia.

[Tan TJian @Rxday000]

Grateful to everyone who built this with me. The work continues 🚀

[vLLM @vllm_project]

🎉 Congrats to our own maintainer Tun Jian Tan @Rxday000, who received the AMD AI Core Contributor award from CEO @LisaSu at #AdvancingAI.

Tun Jian landed the first AMD GPU PR and has led vLLM's ROCm stack for 2.5+ years.

Huge thanks to him, the @EmbeddedLLM team, and the @AIatAMD engineers working alongside them for making high-performance @AMD support a first-class part of vLLM. 🙌

[Tan TJian @Rxday000]

@vllm_project @LisaSu @EmbeddedLLM Thank you @vllm_project! Proud to keep building vLLM with this incredible community

[EmbeddedLLM @EmbeddedLLM]

Singapore has come a long way. 🇸🇬
From AI adoption to AI infrastructure, the local ecosystem is now contributing to the layers production AI depends on: @PyTorch, @vllm_project, inference, sovereign AI, and open-source infra.

Proud to see @RedHat_AI, @inferact, and @EmbeddedLLM building alongside APAC AI community.

[Tan TJian @Rxday000]

@1a1n1d1y I noticed rvLLM supports kernel fusion, does the benchmark include fusion kernel passes on both rvLLM and vLLM?

[EmbeddedLLM @EmbeddedLLM]

🚀 Speed is the MOAT! The ecosystem that ship faster win.
Official ROCm nightly wheels + Docker images are now live for vLLM!
Seamless daily updates with ROCm 7.2.1, PyTorch 2.10 & Triton 3.6.
Thanks for raising this @SemiAnalysis_ big win for the ecosystem.
Props to @AIatAMD and @vllm_project team! Awesome working with you all! 🔥

[vLLM @vllm_project]

Great writeup from @AI21Labs on scaling vLLM for high-throughput, bursty workloads.

TL;DR: systematic config tuning + queue-based autoscaling = 2x throughput from the same GPUs. 🚀

Useful for anyone running vLLM in production with variable traffic patterns.

Thanks to the @AI21Labs team for publishing the full engineering writeup. 💙

🔗 https://t.co/FYBPRHGzHg

[vLLM @vllm_project]

Thanks to @github for spotlighting vLLM in the Octoverse 2025 report — one of the fastest-growing open-source AI projects this year.

🏆 Top OSS by contributors
🚀 Fastest-growing by contributors
🌱 Attracting the most first-time contributors

Trusted by leading open model communities and industry partners — including NVIDIA, Meta, Red Hat, DeepSeek, Qwen, Moonshot, and others — vLLM has become a preferred engine for efficient LLM inference.

With almost 63K stars and 1800 contributors, this growth belongs to the community.

Together, we’re building an easier, faster, and cheaper LLM serving for everyone.

👉https://t.co/O1RFL12qNL
#vLLM #OpenSource #AIInfra #Octoverse

[EmbeddedLLM @EmbeddedLLM]

Big night at the vLLM × Meta × AMD meetup in Palo Alto 💥
So fun hanging out IRL with fellow @vllm_project @woosuk_k, @simon_mo_ and the @AMD crew @AnushElangovan and @roaner.

Bonus: heading home with a signed @RadeonPRO AI Pro R9700 to squeeze even more tokens/sec out of AMD GPUs 🔥

Bonus points if you can guess which signature is @AnushElangovan’s 👀

[Tan TJian @Rxday000]

@drisspg @drisspg How large or a trace file can it load? The web-based perfetto crashes very easily. I am interesting in visualizing a large traces captured from running an LLM.

[Tan TJian @Rxday000]

@JunchenJiang Yes LMCache is amazing!

[EmbeddedLLM @EmbeddedLLM]

@lmcache in @vllm_project Singapore meetup!

[AI at AMD @AIatAMD]

Meet TokenVisor from @EmbeddedLLM: a first of its kind open-source command center for the AMD Instinct neocloud ecosystem.

✅ No proprietary walls
✅ Custom pricing + usage control
✅ Built with AMD, for real AI flexibility

https://t.co/cN5JN0ZnRv

[Lily Liu @eqhylxx]

Yes, I’m very sure vllm is correct — we spent quite a bit of time on that. 🥹

[LMCache Lab @lmcache]

😎Check out how LMCache excels in Multi-Turn Context Chat and RAG use cases in this brief video!

[Tan TJian @Rxday000]

@EmbeddedLLM @vllm_project
isn't just an inference server anymore. It's the de facto standard.

[vLLM @vllm_project]

The @huggingface Transformers ↔️ @vllm_project integration just leveled up: Vision-Language Models are now supported out of the box!

If the model is integrated into Transformers, you can now run it directly with vLLM.

https://t.co/2CHOuZ1iqc

Great work @RTurganbay 👏

[Tan TJian @Rxday000]

@finbarrtimbers This is a common phenomenon in all existing inferencing framework. Different type of kernel and framework optimizations resulted in different order of error accumulation. A example is this https://t.co/iPeaUqVcwY

[llm-d @_llm_d_]

Two new ways to get involved with the llm-d project!

✅ Help shape our roadmap by taking our 5-min survey on your LLM use cases.
✅ Subscribe to our new YouTube channel for tutorials & SIG meetings!

Details in our latest community update: https://t.co/jB5cvq8yRF

[PyTorch @PyTorch]

PyTorch and vLLM are both critical to the AI ecosystem and are increasingly being used together for cutting edge generative AI applications, including inference, post-training, and agentic systems at scale.

🔗 Learn more about PyTorch → vLLM integrations and what’s to come: https://t.co/NscshXM95v

#PyTorch #vLLM #GenerativeAI #OpenSourceAI