Skip to content

feat: Use xllamacpp to allow batching tasks and return reasoning content#258

Open
marcelklehr wants to merge 9 commits into
mainfrom
feat/llama-cpp-server
Open

feat: Use xllamacpp to allow batching tasks and return reasoning content#258
marcelklehr wants to merge 9 commits into
mainfrom
feat/llama-cpp-server

Conversation

@marcelklehr

@marcelklehr marcelklehr commented Jun 18, 2026

Copy link
Copy Markdown
Member
  • Switches llama-cpp-python with xllamacpp a thinner wrapper
  • Make processing async to allow parallel processing
  • Return reasoning content for chat task types

🤖 AI (if applicable)

  • The content of this PR was partly or fully generated using AI

@marcelklehr marcelklehr changed the title feat: Use llama-cpp-server to allow batching tasks feat: Use llama-cpp-server to allow batching tasks and return reasoning content Jun 22, 2026
@marcelklehr marcelklehr changed the title feat: Use llama-cpp-server to allow batching tasks and return reasoning content feat: Use xllamacpp to allow batching tasks and return reasoning content Jun 22, 2026
@marcelklehr marcelklehr marked this pull request as ready for review June 22, 2026 12:06
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
@marcelklehr marcelklehr force-pushed the feat/llama-cpp-server branch from b7253d7 to 975a562 Compare June 22, 2026 12:08
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant