8000 Inferact · GitHub
[go: up one dir, main page]
Skip to content
@Inferact

Inferact

Our mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster.

Popular repositories Loading

  1. tpu-megakernels tpu-megakernels Public

    A collection of megakernels for TPU

    Python 180 16

  2. vllm-frontend-rs vllm-frontend-rs Public archive

    Early-stage Rust drop-in alternative frontend for vLLM

    Rust 73 9

  3. zero-mismatch-rl zero-mismatch-rl Public

    Bitwise-identical token probabilities between RL rollout (vLLM) and training

    25 5

  4. agentx-pareto agentx-pareto Public

    Interactive AgentX throughput-interactivity Pareto explorer with vLLM configuration filters

    JavaScript 1

  5. xgrammar-structural-tag xgrammar-structural-tag Public

    Rust builders for xgrammar structural_tag tool-calling constraints

    Rust 1

  6. openai-harmony openai-harmony Public

    Forked from openai/harmony

    Renderer for the harmony response format to be used with gpt-oss

    Rust

Repositories

Showing 6 of 6 repositories
  • zero-mismatch-rl Public

    Bitwise-identical token probabilities between RL rollout (vLLM) and training

    Inferact/zero-mismatch-rl's past year of commit activity
    25 Apache-2.0 5 0 0 Updated Nov 6, 2026
  • tpu-megakernels Public

    A collection of megakernels for TPU

    Inferact/tpu-megakernels's past year of commit activity
    Python 180 Apache-2.0 16 0 1 Updated Oct 15, 2026
  • xgrammar-structural-tag Public

    Rust builders for xgrammar structural_tag tool-calling constraints

    Inferact/xgrammar-structural-tag's past year of commit activity
    Rust 0 Apache-2.0 1 0 0 Updated Sep 29, 2026
  • agentx-pareto Public

    Interactive AgentX throughput-interactivity Pareto explorer with vLLM configuration filters

    Inferact/agentx-pareto's past year of commit activity
    JavaScript 1 MIT 0 0 0 Updated Aug 7, 2026
  • openai-harmony Public Forked from openai/harmony

    Renderer for the harmony response format to be used with gpt-oss

    Inferact/openai-harmony's past year of commit activity
    Rust 0 Apache-2.0 328 0 0 Updated Jun 25, 2026
  • vllm-frontend-rs Public archive

    Early-stage Rust drop-in alternative frontend for vLLM

    Inferact/vllm-frontend-rs's past year of commit activity
    Rust 73 Apache-2.0 9 0 0 Updated May 22, 2026

Most used topics

Loading…
0