EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

remove cutex dependency (#3422)

Browse Source
This commit is contained in:
Yineng Zhang
2025-02-09 18:33:20 +08:00
committed by GitHub
parent 29daf498cd
commit 4d2dbeaca7
2 changed files with 0 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/backend/speculative_decoding.ipynb
View File

@@ -10,10 +10,6 @@
"\n", "\n",
"**Note:** Currently, Speculative Decoding in SGLang does not support radix cache.\n", "**Note:** Currently, Speculative Decoding in SGLang does not support radix cache.\n",
"\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", "### Performance Highlights\n",
"\n", "\n",
"- Official EAGLE code ([SafeAILab/EAGLE](https://github.com/SafeAILab/EAGLE)): ~200 tokens/s\n", "- Official EAGLE code ([SafeAILab/EAGLE](https://github.com/SafeAILab/EAGLE)): ~200 tokens/s\n",

3
scripts/ci_install_dependency.sh
View File

@@ -19,9 +19,6 @@ pip install torch_memory_saver --force-reinstall
pip install transformers==4.45.2 sentence_transformers accelerate peft pip install transformers==4.45.2 sentence_transformers accelerate peft
# For compling eagle kernels
pip install cutex
# For compling xgrammar kernels # For compling xgrammar kernels
pip install cuda-python nvidia-cuda-nvrtc-cu12 pip install cuda-python nvidia-cuda-nvrtc-cu12