- π Ph.D. in Electrical Engineering from Stanford University.
- π Iβm interested in LLM Inference & Serving, with a focus on Quantization and Parallelism (e.g., Parallel Decoding, Speculative Decoding).
- π± Currently focused on:
- CUDA Kernel Optimization
- Model Deployment & Serving Infrastructure (Paged KV Cache, Continuous Batching)
- Post-training (RLHF, Distillation, Flow-matching)
- π« How to reach me: [email protected]
- π Pronouns: She/Her
π©βπ
building new AI
This repo doesn't represent LF's employer or affiliation.
-
Stanford University, @vllm-project
- California, United States
- https://scholar.google.co.in/citations?hl=en&user=Ft7VbWcAAAAJ
- in/lingling-fan-light-field
Pinned Loading
-
ai-photoshop
ai-photoshop Publiccombine ai generative feature and the photoshop transform-as-you-edit feature
Python
-
openclaw-dating-agent-
openclaw-dating-agent- Publiccopilot dating app reply help in case you are too popular, built upon openclaw
-
-
1point3acres-skill
1point3acres-skill PublicδΈδΊ©δΈεε°.skill β Distilled wisdom from 1point3acres: US study abroad, visa, green card, job hunting & life abroad.
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.