feat: support sm75 with FlashInfer v0.1.6

[zhyncs]

Motivation

support T4

Await https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.1.6

Modifications

Checklist

• Format your code according to the Contributor Guide.
• Add unit tests as outlined in the Contributor Guide.
• Update documentation as needed, including docstrings or example tutorials.

[zhyncs]

python3 -m sglang.launch_server --model Qwen/Qwen2-1.5B-Instruct --mem-fraction-static 0.7

[zhyncs]

Hi @horiacristescu May you try the latest main on T4? Thanks.

# Use the last main branch
git clone https://github.com/sgl-project/sglang.git
cd sglang

pip install --upgrade pip
pip install -e "python[all]"

# Install FlashInfer CUDA kernels
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/

python3 -m sglang.launch_server --model Qwen/Qwen2-1.5B-Instruct --mem-fraction-static 0.7

It works for me on GCP T4.