Yuan Tang
@terrytangyuan.xyz
Senior Principal Software Engineer at Red Hat AI | Open Source Leader at Argo, Kubeflow, Kubernetes, CNCF | Maintainer of KServe, XGBoost, TensorFlow | Keynote Speaker | Author | Technical Advisor
More info: http://terrytangyuan.xyz
We are hiring!
More info: http://terrytangyuan.xyz
We are hiring!
Thanks for the photo!
November 13, 2025 at 4:45 AM
Thanks for the photo!
Thanks for the photos!
November 13, 2025 at 4:45 AM
Thanks for the photos!
Thanks for the photos!
November 11, 2025 at 6:18 PM
Thanks for the photos!
- @kubefloworg.bsky.social & @argoproj.bsky.social
- CNCF TAG Workloads Foundation
- Anything open source, cloud-native, AI infra and systems
Looking forward to meeting old friends and new faces this week!
- CNCF TAG Workloads Foundation
- Anything open source, cloud-native, AI infra and systems
Looking forward to meeting old friends and new faces this week!
November 10, 2025 at 3:51 AM
- @kubefloworg.bsky.social & @argoproj.bsky.social
- CNCF TAG Workloads Foundation
- Anything open source, cloud-native, AI infra and systems
Looking forward to meeting old friends and new faces this week!
- CNCF TAG Workloads Foundation
- Anything open source, cloud-native, AI infra and systems
Looking forward to meeting old friends and new faces this week!
Huge thanks to the 𝗞𝗦𝗲𝗿𝘃𝗲 and 𝗹𝗹𝗺-𝗱 communities for driving this milestone! 🙌
November 6, 2025 at 4:57 PM
Huge thanks to the 𝗞𝗦𝗲𝗿𝘃𝗲 and 𝗹𝗹𝗺-𝗱 communities for driving this milestone! 🙌
With llm-d’s capabilities, including intelligent scheduling, disaggregated prefill-decode serving, distributed inference via vLLM, 𝗞𝗦𝗲𝗿𝘃𝗲 𝗶𝘀 𝘁𝗮𝗸𝗶𝗻𝗴 𝗮 𝗯𝗶𝗴 𝘀𝘁𝗲𝗽 𝘁𝗼𝘄𝗮𝗿𝗱 𝗚𝗲𝗻𝗔𝗜 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲.
November 6, 2025 at 4:57 PM
With llm-d’s capabilities, including intelligent scheduling, disaggregated prefill-decode serving, distributed inference via vLLM, 𝗞𝗦𝗲𝗿𝘃𝗲 𝗶𝘀 𝘁𝗮𝗸𝗶𝗻𝗴 𝗮 𝗯𝗶𝗴 𝘀𝘁𝗲𝗽 𝘁𝗼𝘄𝗮𝗿𝗱 𝗚𝗲𝗻𝗔𝗜 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲.
Learn more: https://kserve.github.io/website/docs/model-serving/generative-inference/llmisvc/llmisvc-overview
Release: https://github.com/kserve/kserve/releases/tag/v0.16.0
Release: https://github.com/kserve/kserve/releases/tag/v0.16.0
November 6, 2025 at 4:57 PM
🚀 Thanks to everyone who subscribed so far!
Kudos to all contributors to this edition! Pete Cheslock, Sasa Zelenovic, Wentao Ye, Nick Hill, Nir Rozenbaum, Jooho Lee, Yuan Tang
Kudos to all contributors to this edition! Pete Cheslock, Sasa Zelenovic, Wentao Ye, Nick Hill, Nir Rozenbaum, Jooho Lee, Yuan Tang
November 5, 2025 at 7:25 PM
🚀 Thanks to everyone who subscribed so far!
Kudos to all contributors to this edition! Pete Cheslock, Sasa Zelenovic, Wentao Ye, Nick Hill, Nir Rozenbaum, Jooho Lee, Yuan Tang
Kudos to all contributors to this edition! Pete Cheslock, Sasa Zelenovic, Wentao Ye, Nick Hill, Nir Rozenbaum, Jooho Lee, Yuan Tang
👉 Check out the November newsletter here: open.substack.com/pub/inferenc...
👉 Subscribe to get future issues in your inbox: inferenceops.substack.com
👉 Subscribe to get future issues in your inbox: inferenceops.substack.com
State of the Model Serving Communities - November 2025
Most recent updates from several AI/ML model inference communities that our teams at Red Hat AI are contributing to.
https://open.substack.com/pub/inferenceops/p/state-of-the-model-serving-communities-ea6?r=3ouig&utm𝘤𝘢𝘮𝘱𝘢𝘪𝘨𝘯=𝘱𝘰𝘴𝘵&𝘶𝘵𝘮medium=web&showWelcomeOnShare=true
November 5, 2025 at 7:25 PM
👉 Check out the November newsletter here: open.substack.com/pub/inferenc...
👉 Subscribe to get future issues in your inbox: inferenceops.substack.com
👉 Subscribe to get future issues in your inbox: inferenceops.substack.com
The response has been incredible - we’ve gained over 𝟴𝟬𝟬 𝘀𝘂𝗯𝘀𝗰𝗿𝗶𝗯𝗲𝗿𝘀! 🎉
Our goal with this newsletter is to give a clear, community-driven view of what’s happening across the model serving ecosystem, including updates from projects like vLLM, KServe, llm-d, @kubernetes.io, Llama Stack, and beyond.
Our goal with this newsletter is to give a clear, community-driven view of what’s happening across the model serving ecosystem, including updates from projects like vLLM, KServe, llm-d, @kubernetes.io, Llama Stack, and beyond.
November 5, 2025 at 7:25 PM
The response has been incredible - we’ve gained over 𝟴𝟬𝟬 𝘀𝘂𝗯𝘀𝗰𝗿𝗶𝗯𝗲𝗿𝘀! 🎉
Our goal with this newsletter is to give a clear, community-driven view of what’s happening across the model serving ecosystem, including updates from projects like vLLM, KServe, llm-d, @kubernetes.io, Llama Stack, and beyond.
Our goal with this newsletter is to give a clear, community-driven view of what’s happening across the model serving ecosystem, including updates from projects like vLLM, KServe, llm-d, @kubernetes.io, Llama Stack, and beyond.
3️⃣ 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗧𝗔𝗚 𝗪𝗼𝗿𝗸𝗹𝗼𝗮𝗱𝘀 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻: 𝗔𝗱𝘃𝗮𝗻𝗰𝗶𝗻𝗴 𝘁𝗵𝗲 𝗖𝗼𝗿𝗲 𝗼𝗳 𝗖𝗹𝗼𝘂𝗱 𝗡𝗮𝘁𝗶𝘃𝗲 𝗘𝘅𝗲𝗰𝘂𝘁𝗶𝗼𝗻: sched.co/27NnE
4️⃣ 𝗡𝗮𝘃𝗶𝗴𝗮𝘁𝗶𝗻𝗴 𝘁𝗵𝗲 𝗥𝗮𝗽𝗶𝗱 𝗘𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗼𝗳 𝗟𝗮𝗿𝗴𝗲 𝗠𝗼𝗱𝗲𝗹 𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲: 𝗪𝗵𝗲𝗿𝗲 𝗗𝗼𝗲𝘀 𝗞𝘂𝗯𝗲𝗿𝗻𝗲𝘁𝗲𝘀 𝗙𝗶𝘁?: sched.co/27Nlv
4️⃣ 𝗡𝗮𝘃𝗶𝗴𝗮𝘁𝗶𝗻𝗴 𝘁𝗵𝗲 𝗥𝗮𝗽𝗶𝗱 𝗘𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗼𝗳 𝗟𝗮𝗿𝗴𝗲 𝗠𝗼𝗱𝗲𝗹 𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲: 𝗪𝗵𝗲𝗿𝗲 𝗗𝗼𝗲𝘀 𝗞𝘂𝗯𝗲𝗿𝗻𝗲𝘁𝗲𝘀 𝗙𝗶𝘁?: sched.co/27Nlv
October 27, 2025 at 3:03 AM
3️⃣ 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗧𝗔𝗚 𝗪𝗼𝗿𝗸𝗹𝗼𝗮𝗱𝘀 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻: 𝗔𝗱𝘃𝗮𝗻𝗰𝗶𝗻𝗴 𝘁𝗵𝗲 𝗖𝗼𝗿𝗲 𝗼𝗳 𝗖𝗹𝗼𝘂𝗱 𝗡𝗮𝘁𝗶𝘃𝗲 𝗘𝘅𝗲𝗰𝘂𝘁𝗶𝗼𝗻: sched.co/27NnE
4️⃣ 𝗡𝗮𝘃𝗶𝗴𝗮𝘁𝗶𝗻𝗴 𝘁𝗵𝗲 𝗥𝗮𝗽𝗶𝗱 𝗘𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗼𝗳 𝗟𝗮𝗿𝗴𝗲 𝗠𝗼𝗱𝗲𝗹 𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲: 𝗪𝗵𝗲𝗿𝗲 𝗗𝗼𝗲𝘀 𝗞𝘂𝗯𝗲𝗿𝗻𝗲𝘁𝗲𝘀 𝗙𝗶𝘁?: sched.co/27Nlv
4️⃣ 𝗡𝗮𝘃𝗶𝗴𝗮𝘁𝗶𝗻𝗴 𝘁𝗵𝗲 𝗥𝗮𝗽𝗶𝗱 𝗘𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗼𝗳 𝗟𝗮𝗿𝗴𝗲 𝗠𝗼𝗱𝗲𝗹 𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲: 𝗪𝗵𝗲𝗿𝗲 𝗗𝗼𝗲𝘀 𝗞𝘂𝗯𝗲𝗿𝗻𝗲𝘁𝗲𝘀 𝗙𝗶𝘁?: sched.co/27Nlv
You can find me at these sessions:
1️⃣ 𝗔𝗻𝗰𝗵𝗼𝗿𝗶𝗻𝗴 𝗧𝗿𝘂𝘀𝘁 𝗶𝗻 𝘁𝗵𝗲 𝗔𝗴𝗲 𝗼𝗳 𝗔𝗜: 𝗜𝗱𝗲𝗻𝘁𝗶𝘁𝗶𝗲𝘀 𝗔𝗰𝗿𝗼𝘀𝘀 𝗛𝘂𝗺𝗮𝗻𝘀, 𝗠𝗮𝗰𝗵𝗶𝗻𝗲𝘀, 𝗮𝗻𝗱 𝗠𝗼𝗱𝗲𝗹𝘀: sched.co/27dCb
2️⃣ 𝗞𝗦𝗲𝗿𝘃𝗲 𝗡𝗲𝘅𝘁: 𝗔𝗱𝘃𝗮𝗻𝗰𝗶𝗻𝗴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗠𝗼𝗱𝗲𝗹 𝗦𝗲𝗿𝘃𝗶𝗻𝗴: sched.co/28D4J
1️⃣ 𝗔𝗻𝗰𝗵𝗼𝗿𝗶𝗻𝗴 𝗧𝗿𝘂𝘀𝘁 𝗶𝗻 𝘁𝗵𝗲 𝗔𝗴𝗲 𝗼𝗳 𝗔𝗜: 𝗜𝗱𝗲𝗻𝘁𝗶𝘁𝗶𝗲𝘀 𝗔𝗰𝗿𝗼𝘀𝘀 𝗛𝘂𝗺𝗮𝗻𝘀, 𝗠𝗮𝗰𝗵𝗶𝗻𝗲𝘀, 𝗮𝗻𝗱 𝗠𝗼𝗱𝗲𝗹𝘀: sched.co/27dCb
2️⃣ 𝗞𝗦𝗲𝗿𝘃𝗲 𝗡𝗲𝘅𝘁: 𝗔𝗱𝘃𝗮𝗻𝗰𝗶𝗻𝗴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗠𝗼𝗱𝗲𝗹 𝗦𝗲𝗿𝘃𝗶𝗻𝗴: sched.co/28D4J
October 27, 2025 at 3:03 AM
You can find me at these sessions:
1️⃣ 𝗔𝗻𝗰𝗵𝗼𝗿𝗶𝗻𝗴 𝗧𝗿𝘂𝘀𝘁 𝗶𝗻 𝘁𝗵𝗲 𝗔𝗴𝗲 𝗼𝗳 𝗔𝗜: 𝗜𝗱𝗲𝗻𝘁𝗶𝘁𝗶𝗲𝘀 𝗔𝗰𝗿𝗼𝘀𝘀 𝗛𝘂𝗺𝗮𝗻𝘀, 𝗠𝗮𝗰𝗵𝗶𝗻𝗲𝘀, 𝗮𝗻𝗱 𝗠𝗼𝗱𝗲𝗹𝘀: sched.co/27dCb
2️⃣ 𝗞𝗦𝗲𝗿𝘃𝗲 𝗡𝗲𝘅𝘁: 𝗔𝗱𝘃𝗮𝗻𝗰𝗶𝗻𝗴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗠𝗼𝗱𝗲𝗹 𝗦𝗲𝗿𝘃𝗶𝗻𝗴: sched.co/28D4J
1️⃣ 𝗔𝗻𝗰𝗵𝗼𝗿𝗶𝗻𝗴 𝗧𝗿𝘂𝘀𝘁 𝗶𝗻 𝘁𝗵𝗲 𝗔𝗴𝗲 𝗼𝗳 𝗔𝗜: 𝗜𝗱𝗲𝗻𝘁𝗶𝘁𝗶𝗲𝘀 𝗔𝗰𝗿𝗼𝘀𝘀 𝗛𝘂𝗺𝗮𝗻𝘀, 𝗠𝗮𝗰𝗵𝗶𝗻𝗲𝘀, 𝗮𝗻𝗱 𝗠𝗼𝗱𝗲𝗹𝘀: sched.co/27dCb
2️⃣ 𝗞𝗦𝗲𝗿𝘃𝗲 𝗡𝗲𝘅𝘁: 𝗔𝗱𝘃𝗮𝗻𝗰𝗶𝗻𝗴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗠𝗼𝗱𝗲𝗹 𝗦𝗲𝗿𝘃𝗶𝗻𝗴: sched.co/28D4J
Our team will review received resumes and get back if there’s good fit.
October 24, 2025 at 9:19 PM
Our team will review received resumes and get back if there’s good fit.
📩 Please 𝗲𝗺𝗮𝗶𝗹 𝗺𝗲 (address in my profile) with a short summary of your background + your resume. www.linkedin.com/in/terrytang...
👉 Not looking right now? Do you know someone who’d be a great fit? Tag them in the comments or share this post - let’s spread the word!
👉 Not looking right now? Do you know someone who’d be a great fit? Tag them in the comments or share this post - let’s spread the word!
October 24, 2025 at 2:39 PM
📩 Please 𝗲𝗺𝗮𝗶𝗹 𝗺𝗲 (address in my profile) with a short summary of your background + your resume. www.linkedin.com/in/terrytang...
👉 Not looking right now? Do you know someone who’d be a great fit? Tag them in the comments or share this post - let’s spread the word!
👉 Not looking right now? Do you know someone who’d be a great fit? Tag them in the comments or share this post - let’s spread the word!
We’re especially excited to meet folks with experience in: Golang, Rust, C++, Kubernetes, distributed systems, and 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲.
If building next-generation distributed AI systems excites you, we’d love to hear from you!
If building next-generation distributed AI systems excites you, we’d love to hear from you!
October 24, 2025 at 2:39 PM
We’re especially excited to meet folks with experience in: Golang, Rust, C++, Kubernetes, distributed systems, and 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲.
If building next-generation distributed AI systems excites you, we’d love to hear from you!
If building next-generation distributed AI systems excites you, we’d love to hear from you!