baseline working model service and perf tooling

This commit is contained in:
2026-07-14 13:57:40 +08:00
parent 1902c81fdd
commit c8cc9401a4
5 changed files with 837 additions and 1 deletions

View File

@@ -42,7 +42,8 @@ cp ./paged_attn.py /usr/local/corex/lib/python3/dist-packages/vllm/attention/ops
python3 ./patch_model_runner.py
# --- transformers: Qwen3_5 tokenizer / model files --------------------------
pip install transformers==4.55.3 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install transformers==4.55.3 -i https://pypi.tuna.tsinghua.edu.cn/simple || \
echo "[patch_ops] WARN: transformers==4.55.3 install failed; continuing with installed transformers."
cp -r ./qwen3_5 /usr/local/lib/python3.10/site-packages/transformers/models/
cp -r ./qwen3_5_moe /usr/local/lib/python3.10/site-packages/transformers/models/
python3 ./patch_transformers_qwen3_5.py