Yineng Zhang
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 3 in the filters
on a stage with
- Philip Kielyonce
who talks about the same things
- Chenyang Zhao3 talks
- Tunji Ruwase2 talks
- Aditya Lohia1 talk
- Mark Saroufim5 talks
- Luca Antiga5 talks
- Philip Kiely6 talks
| title | conference | date |
|---|---|---|
| High Performance LLM Inference in Pure Python with PyTorch Custom Ops | PyCon US 2026 | 2026-05-13 |
Claims a pure-Python inference engine (SGLang/TokenSpeed) reaches parity with TensorRT-LLM by combining a multi-process scheduler, a zero-overhead batch… | ||
| Open Source Model Performance Optimization With SGLang | PyTorch Conference 2025 | 2025-10-22 |
SGLang presents concrete performance wins: flash attention integration, dynamic MHA switching, kernel fusion and DP attention deliver ~2x speed on DeepSE F3… | ||
| Introduction to LLM serving with SGLang | AI Engineer World's Fair 2025 | 2025-06-03 |
SGLang is an open-source serving framework that claims trillions of tokens per day in production and shows day‑zero support for models like DeepSeek and Qwen… | ||
| nothing matches | ||