Skip to content

Update llama batch size help text #387

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
will-lms merged 3 commits into from
May 22, 2026
Merged

Update llama batch size help text #387

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
72b2ef9
Update llama batch size help text
will-lms May 22, 2026
275fdf0
Update llama batch size help copy
will-lms May 22, 2026
d233f8e
Remove unused eval batch size info copy
will-lms May 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions en/config.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,8 +148,8 @@
"llm.load.numCpuExpertLayersRatio/info": "Specifies the number of layers to force the expert into CPU. Leaves attention layers on GPU, saving VRAM while keeping inference fairly fast.",

"llm.load.llama.evalBatchSize/title": "Evaluation Batch Size",
"llm.load.llama.evalBatchSize/subTitle": "Number of input tokens to process at a time. Increasing this increases performance at the cost of memory usage",
"llm.load.llama.evalBatchSize/info": "Sets the number of examples processed together in one batch during evaluation, affecting speed and memory usage",
"llm.load.llama.evalBatchSize/subTitle": "Maximum number of prompt tokens to schedule during prompt processing. Larger values may improve performance, but can use more memory",
"llm.load.llama.physicalBatchSize/subTitle": "Maximum number of prompt tokens to process in one chunk. Larger values may improve performance, but can use more memory",
"llm.load.llama.ropeFrequencyBase/title": "RoPE Frequency Base",
"llm.load.llama.ropeFrequencyBase/subTitle": "Custom base frequency for rotary positional embeddings (RoPE). Increasing this may enable better performance at high context lengths",
"llm.load.llama.ropeFrequencyBase/info": "[Advanced] Adjusts the base frequency for Rotary Positional Encoding, affecting how positional information is embedded",
Expand Down
Loading