From 178be3ccb1c23dc7601642577d01efbf930f4c60 Mon Sep 17 00:00:00 2001 From: Kyle Sayers Date: Wed, 4 Mar 2026 13:25:32 -0500 Subject: [PATCH] update nm to vllm Signed-off-by: Kyle Sayers --- setup.py | 6 +++--- src/llmcompressor/modifiers/README.md | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/setup.py b/setup.py index 6317ab7af6..15daf22c93 100644 --- a/setup.py +++ b/setup.py @@ -86,8 +86,8 @@ def localversion_func(version: ScmVersion) -> str: "local_scheme": localversion_func, "version_file": "src/llmcompressor/version.py", }, - author="Neuralmagic, Inc.", - author_email="support@neuralmagic.com", + author="The vLLM Project", + author_email="vllm-questions@lists.berkeley.edu", description=( "A library for compressing large language models utilizing the " "latest techniques and research in the field for both " @@ -102,7 +102,7 @@ def localversion_func(version: ScmVersion) -> str: "huggingface, compressors, compression, quantization, pruning, " "sparsity, optimization, model optimization, model compression, " ), - license="Apache", + license="Apache 2.0", url="https://github.com/vllm-project/llm-compressor", include_package_data=True, package_dir={"": "src"}, diff --git a/src/llmcompressor/modifiers/README.md b/src/llmcompressor/modifiers/README.md index 63ce233aaf..db4d35fd6f 100644 --- a/src/llmcompressor/modifiers/README.md +++ b/src/llmcompressor/modifiers/README.md @@ -35,7 +35,7 @@ One-shot algorithm that quantizes weights, input activations and/or output activ calculating a range from weights or calibration data. All data is quantized to the closest bin using a scale and (optional) zero point. This basic quantization algorithm is suitable for FP8 quantization. A variety of quantization schemes are supported via the -[compressed-tensors](https://github.com/neuralmagic/compressed-tensors) library. +[compressed-tensors](https://github.com/vllm-project/compressed-tensors) library. ### [GPTQ](./gptq/base.py) One-shot algorithm that uses calibration data to select the ideal bin for weight quantization.