这是indexloc提供的服务,不要输入任何密码
Skip to content

Conversation

@shatfield4
Copy link
Collaborator

@shatfield4 shatfield4 commented Jul 31, 2024

Pull Request Type

  • ✨ feat
  • 🐛 fix
  • ♻️ refactor
  • 💄 style
  • 🔨 chore
  • 📝 docs

Relevant Issues

resolves #1991

What is in this change?

  • Adds a Performance Mode option to the Ollama provider
  • This allows the user to select Base or Maximum
  • Base option, we do not set numCtx
  • Maximum option, we set numCtx to this.promptWindowLimit()

Additional Information

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality
  • Docker build succeeds locally

@timothycarambat timothycarambat merged commit 7273c89 into master Aug 2, 2024
@timothycarambat timothycarambat deleted the 1991-feat-ollama-n_ctx-for-vram-allocation-and-performance-on-responses branch August 2, 2024 20:29
DipFlip pushed a commit to DipFlip/anything-llm that referenced this pull request Aug 4, 2024
* ollama performance mode option

* Change ENV prop
Move perf setting to advanced

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
cabwds pushed a commit to cabwds/anything-llm that referenced this pull request Jul 3, 2025
* ollama performance mode option

* Change ENV prop
Move perf setting to advanced

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
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.

[FEAT]: Ollama n_ctx for VRAM allocation and performance on responses

3 participants