From 34910610520f913201e89921cfcc704c1c32a41a Mon Sep 17 00:00:00 2001 From: binmakeswell Date: Fri, 22 Mar 2024 15:42:25 +0800 Subject: [PATCH 1/3] [release] grok-1 inference --- examples/language/grok-1/README.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/examples/language/grok-1/README.md b/examples/language/grok-1/README.md index c523f941262d..1d234e8eb342 100644 --- a/examples/language/grok-1/README.md +++ b/examples/language/grok-1/README.md @@ -1,5 +1,10 @@ # Grok-1 Inference +An easy-to-use Python + PyTorch + HuggingFace version of 314B Grok-1. +[[code]](https://github.com/hpcaitech/ColossalAI/tree/main/examples/language/grok-1) +[[blog]](https://hpc-ai.com/blog/grok-1-of-pytorch-huggingface-version-is-now-available) +[[HuggingFace Grok-1 PyTorch model weights]](https://huggingface.co/hpcai-tech/grok-1) + ## Install ```bash From 61e1065bd60fda44b93572a35c1daaf7424609f8 Mon Sep 17 00:00:00 2001 From: binmakeswell Date: Fri, 22 Mar 2024 15:43:08 +0800 Subject: [PATCH 2/3] [release] grok-1 inference --- README.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/README.md b/README.md index 7c234b15e75e..d79ec9a66618 100644 --- a/README.md +++ b/README.md @@ -25,6 +25,7 @@ ## Latest News +* [2024/03] [Grok-1 of PyTorch + HuggingFace version is now available!](https://hpc-ai.com/blog/grok-1-of-pytorch-huggingface-version-is-now-available) * [2024/03] [Open-Sora: Revealing Complete Model Parameters, Training Details, and Everything for Sora-like Video Generation Models](https://hpc-ai.com/blog/open-sora-v1.0) * [2024/03] [Open-Sora：Sora Replication Solution with 46% Cost Reduction, Sequence Expansion to Nearly a Million](https://hpc-ai.com/blog/open-sora) * [2024/01] [Inference Performance Improved by 46%, Open Source Solution Breaks the Length Limit of LLM for Multi-Round Conversations](https://hpc-ai.com/blog/Colossal-AI-SwiftInfer) @@ -72,6 +73,7 @@
  • Inference
      +
    • Grok-1: 314B model of PyTorch + HuggingFace Inference
    • SwiftInfer:Breaks the Length Limit of LLM for Multi-Round Conversations with 46% Acceleration
    • GPT-3
    • OPT-175B Online Serving for Text Generation
      • @@ -365,6 +367,12 @@ Please visit our [documentation](https://www.colossalai.org/) and [examples](htt ## Inference +### Grok-1 +An easy-to-use Python + PyTorch + HuggingFace version of 314B Grok-1 Inference. +[[code]](https://github.com/hpcaitech/ColossalAI/tree/main/examples/language/grok-1) +[[blog]](https://hpc-ai.com/blog/grok-1-of-pytorch-huggingface-version-is-now-available) +[[HuggingFace Grok-1 PyTorch model weights]](https://huggingface.co/hpcai-tech/grok-1) +

      From d9383213dc2a53aef882398ce023d16b22d3c56d Mon Sep 17 00:00:00 2001 From: binmakeswell Date: Fri, 22 Mar 2024 15:43:15 +0800 Subject: [PATCH 3/3] [release] grok-1 inference --- docs/README-zh-Hans.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/docs/README-zh-Hans.md b/docs/README-zh-Hans.md index 93045ea6adc6..352564446cfe 100644 --- a/docs/README-zh-Hans.md +++ b/docs/README-zh-Hans.md @@ -24,6 +24,7 @@ ## 新闻 +* [2024/03] [Grok-1 of PyTorch + HuggingFace version is now available!](https://hpc-ai.com/blog/grok-1-of-pytorch-huggingface-version-is-now-available) * [2024/03] [Open-Sora: Revealing Complete Model Parameters, Training Details, and Everything for Sora-like Video Generation Models](https://hpc-ai.com/blog/open-sora-v1.0) * [2024/03] [Open-Sora：Sora Replication Solution with 46% Cost Reduction, Sequence Expansion to Nearly a Million](https://hpc-ai.com/blog/open-sora) * [2024/01] [Inference Performance Improved by 46%, Open Source Solution Breaks the Length Limit of LLM for Multi-Round Conversations](https://hpc-ai.com/blog/Colossal-AI-SwiftInfer) @@ -71,6 +72,7 @@
    • 推理