Skip to content
View Lidang-Jiang's full-sized avatar

Block or report Lidang-Jiang

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.

Maximum 250 characters. Please don’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 user’s behavior. Learn more about reporting abuse.

Report abuse
Lidang-Jiang/README.md

Hi, I'm Lidang Jiang

MLsys Engineer passionate about using AI to build everything — from inference systems to embodied robots.

Interests: Embodied AI, Robotics, Inference Acceleration, AI Infra, C++

Blog GitHub


Open Source Contributions

51 merged PRs across 22 projects (948.6k+ combined stars) · 62 open PRs in review

Repository Stars PRs Merged Links
openclaw/openclaw 369.5k 1 #66285
affaan-m/everything-claude-code 175.3k 5 View all
huggingface/transformers 160.4k 1 #45045
vllm-project/vllm 79.3k 1 #38099
docker/compose 37.3k 1 #13684
Genesis-Embodied-AI/genesis-world 28.7k 6 View all
sgl-project/sglang 27.2k 2 #21400, #21399
Farama-Foundation/Gymnasium 11.8k 1 #1553
OpenRLHF/OpenRLHF 9.5k 1 #1212
apify/crawlee-python 8.9k 1 #1835
open-edge-platform/anomalib 5.7k 3 #3509, #3508, #3512
rllm-org/rllm 5.5k 1 #480
vllm-project/vllm-omni 4.6k 4 View all
pytorch/executorch 4.6k 2 #18703, #18701
Lightning-AI/LitServe 3.9k 2 #673, #674
pytorch/rl 3.4k 1 #3593
Farama-Foundation/HighwayEnv 3.2k 1 #668
haosulab/ManiSkill 2.9k 2 #1403, #1402
pytorch/ao 2.8k 1 #4242
microsoft/Olive 2.3k 1 #2380
FreeOpcUa/opcua-asyncio 1.4k 4 View all
baidu/vLLM-Kunlun 407 9 View all

Merged PR Details

affaan-m/everything-claude-code (5 merged PRs)
  • #992 - fix(hooks): port doc-file-warning denylist policy to current hook runtime
  • #972 - fix(observer): improve Windows compatibility for temp files and Haiku prompt
  • #974 - fix(codex): add persistent_instructions to baseline and relax sanity check
  • #971 - fix(codex): add startup_timeout_sec to MCP servers to prevent first-run timeouts
  • #977 - fix(scripts): add os.homedir() fallback for Windows compatibility

Genesis-Embodied-AI/genesis-world (6 merged PRs)
  • #2653 - [BUG FIX] Fix GPU detection in test infrastructure for WSL2
  • #2614 - [BUG FIX] Fix sensor camera 'lookat' being ignored when 'entity_idx' is set.
  • #2613 - [FEATURE] Add public API to RigidEntity for kinematic and potential energy.
  • #2612 - [BUG FIX] Fix IK solver using wrong entity's DOFs for multi-robot scenes.
  • #2609 - [MISC] Rename 'Drone.set_propellels_rpm' in 'Drone.set_propellers_rpm'.
  • #2610 - [BUG FIX] Fix motion planning crashing for short path < 3 nodes.

vllm-project/vllm-omni (4 merged PRs)
  • #1636 - [Bugfix] Fix missing ANSI colors in CLI logo when output is piped
  • #2228 - [Cleanup] Replace bare print() with logger and use specific exception types
  • #2221 - [Misc] Make gradio an optional dependency and upgrade to >=6.7.0
  • #1687 - [BugFix] Return proper HTTP status for ErrorResponse in create_speech

FreeOpcUa/opcua-asyncio (4 merged PRs)
  • #1956 - Fix PubSub UdpSettings key name case mismatch and TTL type check
  • #1957 - Widen type annotations for reference methods to accept NodeId
  • #1955 - Fix PubSub DataSetWriter sequence number uint16 overflow
  • #1954 - Fix load_certificate/load_private_key ignoring explicit format argument

baidu/vLLM-Kunlun (9 merged PRs)
  • #341 - [Doc] Fix XProfiler benchmark documentation typos
  • #328 - [Doc] Clarify Docker image tags and pull checks
  • #327 - [Doc] Fix invalid installation checkout reference
  • #249 - [Bugfix]: update version numbers to 0.15.1
  • #253 - [Doc] Remove --compilation-config from all docs
  • #251 - [Doc] Fix 5 Sphinx warnings causing Read the Docs build failure
  • #218 - [Misc] add collect_env feat
  • #136 - [Doc] Optimize the document
  • #108 - [Bug] Fix InternVL KeyError: ((1, 1, 3), '<i8')

Tech Stack

Python C++ Go TypeScript CUDA PyTorch Kubernetes Docker

Popular repositories Loading

  1. vLLM-Kunlun vLLM-Kunlun Public

    Forked from baidu/vLLM-Kunlun

    vLLM Kunlun (vllm-kunlun) is a community-maintained hardware plugin designed to seamlessly run vLLM on the Kunlun XPU.

    Python 1 1

  2. Lidang-Jiang.github.io Lidang-Jiang.github.io Public

    personal websites

    TypeScript

  3. UniversityResearcherProfiles UniversityResearcherProfiles Public

    Vue

  4. vllm-omni vllm-omni Public

    Forked from vllm-project/vllm-omni

    A framework for efficient model inference with omni-modality models

    Python

  5. sglang sglang Public

    Forked from sgl-project/sglang

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Python

  6. vllm vllm Public

    Forked from vllm-project/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Python