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

chore: add hf_xet dep (#6243)

Browse Source
This commit is contained in:
Yineng Zhang
2025-05-12 13:08:40 -07:00
committed by GitHub
parent e8e18dcdcc
commit f94543d22b
3 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/eval/loogle_eval.py
View File

@@ -142,7 +142,7 @@ if __name__ == "__main__":
parser.add_argument( parser.add_argument(
"--model", "--model",
default="meta-llama/Llama-4-Maverick-17B-128E-Instruct", default="meta-llama/Llama-4-Maverick-17B-128E-Instruct",
help="Model name or ID", help="Model name or ID, only used for model name",
) )
parser.add_argument( parser.add_argument(
"--max-concurrency", type=int, default=144, help="Maximum concurrent requests" "--max-concurrency", type=int, default=144, help="Maximum concurrent requests"

3
scripts/ci_install_dependency.sh
View File

@@ -31,3 +31,6 @@ pip install -e lmms-eval/
# Install FlashMLA for attention backend tests # Install FlashMLA for attention backend tests
pip install git+https://github.com/deepseek-ai/FlashMLA.git pip install git+https://github.com/deepseek-ai/FlashMLA.git
# Install hf_xet
pip install huggingface_hub[hf_xet]

3
scripts/ci_install_dependency_8_gpu.sh
View File

@@ -123,3 +123,6 @@ gdrcopy_copybw
echo "=== Verify NVSHMEM ===" echo "=== Verify NVSHMEM ==="
nvshmem-info -a nvshmem-info -a
# /opt/nvshmem/bin/perftest/device/pt-to-pt/shmem_put_bw # /opt/nvshmem/bin/perftest/device/pt-to-pt/shmem_put_bw
# Install hf_xet
pip install huggingface_hub[hf_xet]