Open Bug 2046850 (llama-cpp-baseline) Opened 1 month ago Updated 16 days ago

[meta] On-device memories milestone 1 - Tighten up baseline implementation

Categories

(Core :: Machine Learning: On Device, task)

Product:
Core
Component:
Machine Learning: On Device
Type:
task

Tracking

()

People

(Reporter: gregtatum, Unassigned)

References

(Depends on 3 open bugs)

Details

(Keywords: meta, Whiteboard: [aiplatform])

In order to ship on-device models for text generation we want to tighten up the existing implementation. This is a meta bug to collect that work for tracking purposes.

Depends on: 2043658
Whiteboard: [aiplat]
Depends on: 2046971
Depends on: 2047021
Depends on: 2047188
Depends on: 2043430
Depends on: 2047023
Depends on: 2047025
Depends on: 2047026
Whiteboard: [aiplat] → [aiplatform]
Summary: [meta] Tighten up baseline llama.cpp implementation → [meta] llama.cpp Phase 1 - Tighten up baseline implementation
Summary: [meta] llama.cpp Phase 1 - Tighten up baseline implementation → [meta] On-device memories milestone 1 - Tighten up baseline implementation
You need to log in before you can comment on or make changes to this bug.