Yineng Zhang
Employers on the program
- 2025–2026Together AI2 talks
- 2025SGLang1 talk
The year around now
Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.
Appearances by year
- AI Engineer (World's Fair, Summit and regional editions)
- PyCon (national Python conferences)
- PyTorch Conference
Talks
| Date | Event | Conference | Role | Title | Links |
|---|---|---|---|---|---|
| May 13, 2026 | PyCon US 2026 | PyCon (national Python conferences) | speaker | High-Performance LLM Inference in Pure Python with PyTorch Custom Ops as Together AI This talk presents how a modern large language model (LLM) inference engine written entirely in Python can reach performance comparable to C++-based systems…Show lessThis talk presents how a modern large language model (LLM) inference engine written entirely in Python can reach performance comparable to C++-based systems such as TensorRT-LLM. | Video |
| Oct 22, 2025 | PyTorch Conference 2025 | PyTorch Conference | speaker | Open Source Model Performance Optimization With SGLang as Together AI SGLang is an open-source fast inference framework in the PyTorch ecosystem built for performant, flexible, extensible model serving. SGLang's growing popularity…Show lessSGLang is an open-source fast inference framework in the PyTorch ecosystem built for performant, flexible, extensible model serving. SGLang's growing popularity is in large part thanks to its community ethos and the participation of developers from around the world. Join this BoF session hosted by... | |
| Jun 3, 2025 | AI Engineer World's Fair 2025 | AI Engineer (World's Fair, Summit and regional editions) | workshop | Introduction to LLM serving with SGLang as SGLang Do you want to learn how to serve models like DeepSeek and Qwen with SOTA speeds on launch day? SGLang is an open-source fast serving framework for LLMs and…Show lessDo you want to learn how to serve models like DeepSeek and Qwen with SOTA speeds on launch day? SGLang is an open-source fast serving framework for LLMs and VLMs that generates trillions of tokens per day at companies like xAI, AMD, and Meituan. | Video |
Frequent co-speakers
| Speaker | Shared events | Shared talks | Last together |
|---|---|---|---|
| Philip Kiely | 2 | 1 | 2025 |
| Jonathan Dekhtiar | 2 | — | 2026 |
| Niels Bantilan | 2 | — | 2026 |
| Sarah Kaiser | 2 | — | 2026 |
| Steven Troxler | 2 | — | 2026 |
| Daniel Han | 2 | — | 2025 |
| Dylan Patel | 2 | — | 2025 |
| Jerry Liu | 2 | — | 2025 |
| Nathan Lambert | 2 | — | 2025 |
| Samuel Colvin | 2 | — | 2025 |
| Sarah Guo | 2 | — | 2025 |
Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.