Skip to content

ENH: Support xllamacpp#2997

Merged
qinxuye merged 14 commits into
xorbitsai:mainfrom
codingl2k1:feat/concurrent_llama_cpp_server
Mar 9, 2025
Merged

ENH: Support xllamacpp#2997
qinxuye merged 14 commits into
xorbitsai:mainfrom
codingl2k1:feat/concurrent_llama_cpp_server

Conversation

@codingl2k1

@codingl2k1 codingl2k1 commented Mar 4, 2025

Copy link
Copy Markdown
Contributor

Disabled by default, can be enabled by setting env USE_XLLAMACPP=1

@XprobeBot XprobeBot added the enhancement New feature or request label Mar 4, 2025
@XprobeBot XprobeBot added this to the v1.x milestone Mar 4, 2025
@codingl2k1
codingl2k1 marked this pull request as ready for review March 6, 2025 20:03

@qinxuye qinxuye left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Really excellent work, I left some comments.

Comment thread xinference/client/tests/test_client.py Outdated
Comment thread xinference/model/llm/llama_cpp/core.py
Comment thread xinference/model/llm/llama_cpp/core.py
@qinxuye

qinxuye commented Mar 7, 2025

Copy link
Copy Markdown
Contributor

I found that now the lock would exist for Xllamacpp, and I added a commit to release it.

@qinxuye
qinxuye force-pushed the feat/concurrent_llama_cpp_server branch from 39f23db to f54db47 Compare March 8, 2025 12:54
@qinxuye
qinxuye force-pushed the feat/concurrent_llama_cpp_server branch from 2cd5059 to 7eea8f8 Compare March 9, 2025 03:06

@qinxuye qinxuye left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@qinxuye
qinxuye merged commit 5d6ec93 into xorbitsai:main Mar 9, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants