Tavondo
CompetitionsEventsGuidesPlatforms
中文Start matching
CompetitionsEventsGuidesPlatforms
中文Sign in
Tavondo

Find AI competitions and events worth your time.

CompetitionsEventsGuidesPlatforms
Sign inRegisterStart matching

© 2026 Tavondo

中文
  1. Home
  2. Competitions
  3. AMD X「GPU MODE E2E SpeedRun」线上黑客松挑战赛
ModelScopeLLMIntermediateRegistration closed

AMD X「GPU MODE E2E SpeedRun」线上黑客松挑战赛

A intermediate llm competition requiring roughly 10–30 hours for an end-to-end practice run.

Difficulty
Intermediate
Estimated effort
10–30 hours
Registration deadline
Apr 6, 2026
Compute
Free GPU OK
OverviewPreparationSource

Overview

Who this competition fits

适合已有 GPU 内核开发和大语言模型推理性能优化经验的开发者或研究团队,尤其是能处理 MXFP4、MoE、MLA Decode,以及 AMD ATOM、SGLang 或 vLLM 推理栈的人。决赛参与者还需要能在 AMD Instinct 多卡环境中调优 DeepSeek-R1 或 Kimi K2.5 的端到端推理。

Read the original official blurb
本次黑客松总奖金池为110 万美元。赛事聚焦 GPU kernel 优化与端到端(E2E)推理加速。参赛者将在真实 LLM 负载上交付可观的性能提升,并展示在AMD GPU 性能工程方面的创新方法。 Official category: hackathon. Participants: 0. Organizers: AMD.

Preparation

From registration to a first submission

  1. 01

    AMD GPU 内核优化

  2. 02

    MXFP4 与 GEMM

  3. 03

    MoE 与 MLA Decode

  4. 04

    LLM 推理框架(AMD ATOM、SGLang 或 vLLM)

  5. 05

    多 GPU 并行配置(TP/EP)

  6. 06

    Git Pull Request 与代码合并

Before you commit: 难点不只是跑得快,而是要同时在多个并发等级满足吞吐、交互性、端到端延迟与精度条件。获奖代码还必须在最终评选后可合并到指定的 AMD 官方仓库,这要求实现具备工程可维护性和上游兼容性。

Source

How this page was assembled

Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.

Official competition page
ModelScope
Registration
Open signup form
Last checked
Mar 15, 2026

Entry assessment

est.
55

Prepare before joining

Overall fit estimate

Beginner fit55/100
Learning value58/100

Confirm eligibility and time commitment before moving into formal preparation.

18+

Open official pageSign in to saveOpen guide

Timeline

Registration opens
Mar 7, 2026
Registration deadline
Apr 6, 2026

Data and review state

Separate what is confirmed from what still needs review. Official rules and deadlines win.

View data stateClose
Source page verifiedMetric confirmedReviewed
Source published
Mar 15, 2026
Published on this site
Aug 11, 2026

Official metric is not published on the ModelScope competition listing; verify scoring on the competition page.

reward_value_usd is a rough CNY→USD estimate (×0.14) for ranking only; use reward_summary for the official prize text.