llama.cpp topics
12 short topics in Generative AI and LLM Applications. Each one is a single focused exercise with a clear piece of evidence at the end.
12 topics, one exercise each.
Work through them in order, or jump to the one you need.
These are draft topic outlines (draft; instructor review pending). Full lessons follow after review; ask Ajay if you need a topic sooner.
- 01
Model artifact compatibility
Investigate model artifact compatibility using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 02
Model loading and startup
Investigate model loading and startup using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 03
Inference request batching
Investigate inference request batching using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 04
Execution device selection
Investigate execution device selection using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 05
Numeric precision choices
Investigate numeric precision choices using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 06
Memory and context limits
Investigate memory and context limits using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 07
Request scheduling and throughput
Investigate request scheduling and throughput using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 08
Streaming inference integration
Investigate streaming inference integration using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 09
Server or local-process lifecycle
Investigate server or local-process lifecycle using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 10
Health and diagnostic evidence
Investigate health and diagnostic evidence using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 11
Inference benchmark design
Investigate inference benchmark design using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 12
Model update and rollback strategy
Investigate model update and rollback strategy using a repeatable llama.cpp experiment; compare results with a baseline and record limitations. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course →
Learn the same ideas beyond llama.cpp.
These courses share topics with this one, so you can compare how each language or tool handles the same concept.
More in AI APIs inference and local models.
You have the curiosity.
Let’s turn it into capability.
Start with a practical workshop or bring a specific question to Ajay.