From 4d2dbeaca7d942c5374902cfcf31365f8452b5d5 Mon Sep 17 00:00:00 2001 From: Yineng Zhang Date: Sun, 9 Feb 2025 18:33:20 +0800 Subject: [PATCH] remove cutex dependency (#3422) --- docs/backend/speculative_decoding.ipynb | 4 ---- scripts/ci_install_dependency.sh | 3 --- 2 files changed, 7 deletions(-) diff --git a/docs/backend/speculative_decoding.ipynb b/docs/backend/speculative_decoding.ipynb index 273d943d1..7103469fc 100644 --- a/docs/backend/speculative_decoding.ipynb +++ b/docs/backend/speculative_decoding.ipynb @@ -10,10 +10,6 @@ "\n", "**Note:** Currently, Speculative Decoding in SGLang does not support radix cache.\n", "\n", - "To run the following tests or benchmarks, you also need to install [**cutex**](https://pypi.org/project/cutex/): \n", - "\n", - "`pip install cutex`\n", - "\n", "### Performance Highlights\n", "\n", "- Official EAGLE code ([SafeAILab/EAGLE](https://github.com/SafeAILab/EAGLE)): ~200 tokens/s\n", diff --git a/scripts/ci_install_dependency.sh b/scripts/ci_install_dependency.sh index ffe405d5a..cce3042f4 100755 --- a/scripts/ci_install_dependency.sh +++ b/scripts/ci_install_dependency.sh @@ -19,9 +19,6 @@ pip install torch_memory_saver --force-reinstall pip install transformers==4.45.2 sentence_transformers accelerate peft -# For compling eagle kernels -pip install cutex - # For compling xgrammar kernels pip install cuda-python nvidia-cuda-nvrtc-cu12