Skip to content
View lengrongfu's full-sized avatar

Organizations

@kubernetes @Project-HAMi

Block or report lengrongfu

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse

Pinned Loading

  1. containerd/containerd Public

    An open and reliable container runtime

    Go 18.7k 3.6k

  2. kubernetes/kubernetes Public

    Production-Grade Container Scheduling and Management

    Go 116k 40.7k

  3. HAMi Public

    Forked from Project-HAMi/HAMi

    OpenAIOS vGPU scheduler for Kubernetes is originated from the OpenAIOS project to virtualize GPU device memory.

    Go

  4. vllm Public

    Forked from vllm-project/vllm

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

    Python

  5. mpu Public

    Forked from limstash/mpu

    A shim driver allows in-docker nvidia-smi showing correct process list without modify anything

    C 3 1

579 contributions in the last year

Contribution Graph
Day of Week June July August September October November December January February March April May June
Sunday
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More

Contribution activity

June 2025

Created 2 commits in 2 repositories

Created a pull request in vllm-project/vllm that received 1 comment

[nvidia] add support Nvidia Multi-Instance GPU device

FIX #17047 Becase MIG device is diffrent other nvidia device, so we need two handler mig special device.

+80 −11 lines changed 1 comment
Reviewed 2 pull requests in 1 repository
Project-HAMi/HAMi 2 pull requests

Created an issue in vllm-project/vllm that received 5 comments

[Feature]: asyncio_mode and not multiprocess_mode EngineCore imple

🚀 The feature, motivation and pitch vllm/vllm/v1/engine/core_client.py Lines 64 to 69 in 02658c2 This todo is it still necessary to imp…

1 task done
5 comments
Loading