LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

  • Markets
  • Builders
  • Research
  • Ecosystems
  • Launchpads
  • Search
Ecosystems

Other

InferenceX

Open Source Continuous Inference Benchmarking Qwen3.5, DeepSeek, GPTOSS - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 vs H100 & soon™ TPUv6e/v7/Trainium2/3

OtherEmerging
GitHubWebsite
Stars
—
Forks
—
Contributors
8
Last push
2mo ago

Recent commits

Latest commits.

  • Add H200 config: dsv4-fp8-vllm (DeepSeek-V4-Pro) (#1130)
    6f3c1c0functionstackx2mo ago
  • [AMD/ROCM] atom qwen fp8/fp8_mtp3 on mi355x (#1040)
    80b284aseungrokj2mo ago
  • Reduce PR sweep breadth via process_changelog (#1123)
    0b0c7c4Bryan Shan2mo ago
  • [AMD/ROCM] atom glm5.1 fp4 on mi355x (#1043)
    69b4201seungrokj2mo ago
  • Remove atom-specific squash file deletion before import (#1124)
    5adb7f9seungrokj2mo ago
trigger H100 multinode evals (#1120)
ed6006eBryan Shan2mo ago
  • trigger H100 multinode evals (#1119)
    8bda39fBryan Shan2mo ago
  • increase H100 timeout (#1117)
    ad9b5c8Bryan Shan2mo ago

    • Top contributors

    Builders behind this project.

    kimbochen
    423 commits
    functionstackx
    182 commits
    cquil11
    155 commits
    Oseltamivir
    65 commits
    kedarpotdar-nv
    63 commits
    dependabot[bot]
    20 commits
    KaunilD
    19 commits
    Copilot
    17 commits