Skip to content
View ethanhq's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing
12 followers · 0 following
  • 11:35 (UTC -12:00)

Achievements

Achievement: Pair Extraordinairex3Achievement: Starstruckx2Achievement: Pull Sharkx2

Achievements

Achievement: Pair Extraordinairex3Achievement: Starstruckx2Achievement: Pull Sharkx2

Block or report ethanhq

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 donโ€™t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
ethanhq/README.md
Hi there! I'm Ethan Guo
Roles

email X

3+ years of backend engineering ยท now focused on AI Agents & LLM-powered applications

โš’๏ธ Skills

  • ๐Ÿค– AI Agents & Infra: Long-horizon agents โ€” context engineering, harness design, multi-agent orchestration, MCP & Skills; LLM inference optimization โ€” GPU kernels, speculative decoding, KV & prompt caching, quantization, profiling & benchmarking.
  • ๐Ÿ–ฅ๏ธ Full-Stack: End-to-end product delivery โ€” API design (REST/GraphQL), authentication & authorization, async backends, modern frontends (React/Next.js/Vue), CI/CD pipelines, and cloud deployment.
  • ๐ŸŒ Distributed Systems: Scalable architectures โ€” service decomposition, message queues (Kafka/RabbitMQ), event-driven workflows, distributed caching, consistency & fault tolerance, and cloud-native microservices on Kubernetes.

๐Ÿ”ฅ Achievements

  • ๐Ÿ… llama.cpp highlight PR #29570 โ€” Metal flash-attention kernel for Apple M5 GPUs: ~2ร— attention throughput, +45% prompt processing at 32K context.

๐ŸŒฑ Open Source Contributions

๐Ÿ› ๏ธ Projects I Maintain

Project Description Stars
ethanhq/cc-fleet Run Claude Code's Dynamic Workflows, Agent Teams & Subagents on any third-party model โ€” DeepSeek, GLM, Qwen โ€ฆ or your Codex subscription. No Anthropic subscription needed. Stars

๐Ÿค Contributions to Other Projects

Project Description Stars PRs
ggml-org/llama.cpp LLM inference in C/C++ Stars #29570 Tensor-API flash attention kernel for Apple M5 GPUs
#29638 Stop accepting speculative draft tokens at EOG
#30491 BF16 variant of the M5 flash attention kernel
NousResearch/hermes-agent Self-improving AI agent Stars #19576 Recover cron jobs stuck without a next run time
#25788 Handle reasoning-only stream chunks from Gemini
nexu-io/open-design Open-source Claude Design alternative Stars #5121 Block SSRF in brand-extraction fetches
#5146 Fix Windows command injection in host-tool launch
#5113 Fix ReDoS in design-system swatch parsers
#5027 Reject path-traversal IDs in prompt templates
#5847 Sanitize deck thumbnail markup with DOMPurify
#2110 Parse DESIGN.md YAML frontmatter for presets
#1951 Manual removal of captured Pod components
#5740 Abort oversized or failed Composio logo fetches
merged PRs More fixes, features & test coverage

๐Ÿ‰ Tech Stack

Languages

Languages

Backend & Frameworks

Backend

Frontend

Frontend

Databases & Messaging

Data

DevOps & Infrastructure

DevOps

Pinned Loading

  1. cc-fleet cc-fleet Public

    ๐Ÿšข Run Claude Code's โš™๏ธ Dynamic Workflows, ๐Ÿ‘ฅ Agent Teams & โšก Subagents on any third-party model โ€” DeepSeek ยท GLM ยท Kimi ยท Qwen โ€ฆ or your Codex subscription. No Anthropic subscription needed. ๏ฝœ ๐Ÿšข ่ฎฉ Cโ€ฆ

    Go 144 26

  2. ggml-org/llama.cpp ggml-org/llama.cpp Public

    LLM inference in C/C++

    C++ 132k 24.5k