GitLab

🔧 update config.yaml setting default config

Update modeling_deepseek_v3.py

slove [Bug] #1023

文档更新：model_path名字要求以及在示例中添加force_think

* add documentations about `--model_path` requirements
* add `--force_think` in doc (most users would run R1 and would want it to provide reasoning process)

Only modified the mixed single and double quotes in server/config/config.py

fix local_chat bug and update doc

Update SUMMARY.md

delete sudo install

yaml: fix Marlin AssertionError

fix: refine backend error message to include ROCM_HOME

Update balance-serve.md

In v0.2.4 version, we’ve added highly desired multi-concurrency support to the community through a major refactor of the whole architecture.

Fix db position issue

Signed-off-by: fishingfly <zhoyuzf@163.com>

Update README.md

Marlin quantized linear only supports GPU device, when change generate_op
to "KLinearMarlin", generate_device need to be changed to "cuda" accordingly.

Fixes: e5b001d7 ("Update readme; Format code; Add example yaml.")

fix benchmark params for human eval benchmark