From d4e55bad11bba009a34442088df897528785c368 Mon Sep 17 00:00:00 2001 From: Sage Moore Date: Wed, 10 Apr 2024 07:23:19 -0400 Subject: [PATCH] add test_compressed_memory to skipped list --- README.md | 1 + neuralmagic/tests/skip-for-remote-push.txt | 1 + 2 files changed, 2 insertions(+) diff --git a/README.md b/README.md index cf86c30e82d7d..9941b8abd977b 100644 --- a/README.md +++ b/README.md @@ -5,6 +5,7 @@ [vLLM](https://github.com/vllm-project/vllm) is a fast and easy-to-use library for LLM inference that Neural Magic regularly contributes upstream improvements to. This fork, `nm-vllm` is our opinionated focus on incorporating the latest LLM optimizations like quantization and sparsity for enhanced performance. ## Installation +The [nm-vllm PyPi package](https://pypi.org/project/nm-vllm/) includes pre-compiled binaries for CUDA (version 12.1) kernels, streamlining the setup process. For other PyTorch or CUDA versions, please compile the package from source. Install it using pip: ```bash diff --git a/neuralmagic/tests/skip-for-remote-push.txt b/neuralmagic/tests/skip-for-remote-push.txt index 67a07fe4bdbcd..110b54f8e6fc6 100644 --- a/neuralmagic/tests/skip-for-remote-push.txt +++ b/neuralmagic/tests/skip-for-remote-push.txt @@ -12,6 +12,7 @@ tests/distributed/test_comm_ops.py tests/prefix_caching/test_prefix_caching.py tests/models/test_models_logprobs.py tests/models/test_models.py +tests/models/test_compressed_memory.py tests/spec_decode/test_utils.py tests/spec_decode/test_spec_decode_worker.py tests/spec_decode/test_metrics.py