Skip to content
View wuxuedaifu's full-sized avatar
:octocat:
:octocat:
7 followers · 39 following
  • Xiaomi
  • Beijing
  • 00:17 (UTC -12:00)

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull SharkAchievement: Starstruck

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull SharkAchievement: Starstruck

Block or report wuxuedaifu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
wuxuedaifu/README.md

Data Scientist with a production engineering side. I work on AI systems that have to run reliably at inference time — not just in notebooks.

Current focus: multimodal AI serving (TTS, OCR, ASR, LLM) on GPU infrastructure.

Production serving systems

vLLM-based serving repos with real benchmark data on A100 / H200.

All expose OpenAI-compatible APIs and ship with Docker.

Data science work

  • ASR / TTS: speech systems, streaming inference, latency optimization
  • Vision: OCR, face recognition, document AI
  • LLM: RAG pipelines, serving infra, OpenAI-compatible APIs
  • Data: ClickHouse, PostgreSQL, ETL pipelines, AQI/weather data systems

Stack

Python · vLLM · FastAPI · CUDA · Docker · Kubernetes
ClickHouse · PostgreSQL · Java · SQL

Pinned Loading

  1. vllm-surya-ocr vllm-surya-ocr Public

    OpenAI-compatible, vLLM-served OCR API for the Surya-OCR-2 model — multilingual document OCR (layout + text recognition) with request batching, a local CLI, and Docker packaging.

    Python 4

  2. xttsv2-vllm-streaming-server xttsv2-vllm-streaming-server Public

    Real-time streaming TTS server for XTTS-v2 on vLLM — OpenAI-compatible API, ~0.5s TTFB, Docker

    Python 8 1

  3. vllm-chatterbox-stream vllm-chatterbox-stream Public

    OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cloning, and 23 languages.

    Python 8

  4. pipecat-plugin-tenvad pipecat-plugin-tenvad Public

    Local TenVAD voice activity detection plugin for Pipecat voice agent pipelines

    Python 4

  5. deepfilter-stream deepfilter-stream Public

    Real-time streaming noise cancellation with DeepFilterNet3 on ONNX Runtime

    Python 6 1