0z5a (0z5a) · GitHub
Skip to content
View 0z5a's full-sized avatar
🏠
Working from home
🏠
Working from home
54 followers · 44 following
  • University of Tübingen
  • Tübingen
  • 00:28 (UTC +08:00)
  • X @0z5aa

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx2Achievement: Quickdraw

Block or report 0z5a

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. 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
0z5a/README.md

/0z5a — a pixel startup command with a blinking cursor. White and baby-blue desktop with projects, open source, a toolbox and an animated cyber sleepy cat.

InfraSWEFlashNSViperEkura/AstrAI
vllm-project/vllmvllm-project/vllm-omnideepspeedai/DeepSpeed
llm-dByteDance-Seed/VeOmnikvcache-ai/Mooncakevllm-project/vime
uccl-project/ucclNVIDIA/ncclNVIDIA/cudnn-frontendProject-HAMi/HAMiflashinfer-ai/flashinfer
verl-project/verl-omniNVlabs/cuda-oxideNVIDIA/TransformerEnginesgl-project/sglang
NVIDIA/cuda-rustNVlabs/parrotInferMatrixLab/vllm-rltmlc-ai/xgrammar

GitHub stats

Pinned Loading

  1. vllm-project/vllm vllm-project/vllm Public

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

    Python 94.8k 23.7k

  2. deepspeedai/DeepSpeed deepspeedai/DeepSpeed Public

    DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

    Python 43.3k 5.1k

  3. InfraSWE InfraSWE Public

    InfraSWE is an executable benchmark and certification framework for AI infrastructure agents.

    Python 1

  4. FlashNS FlashNS Public

    FP64 Taylor-jet PINN kernels: 5.35x vs PhysicsNeMo and 4.35x vs PyTorch nested AD in the recorded H100 NVL Kovasznay solve (3-seed median accepted-run times after budget extension); explicit gradie…

    Python 1