Learning center

Learn only what changes the capacity plan.

Each guide resolves one decision in an inference, vLLM serving, LoRA, or QLoRA workload baseline.

Memory model

Separate model weights, KV Cache, and runtime reserve

A parameter count alone cannot tell you whether a model will fit at the context length and concurrency you need.

Read guide →

Serving capacity

Plan context length and concurrency together

A model that fits for one chat can run out of capacity once long requests or parallel users share the same GPU.

Read guide →

vLLM model length

Set vLLM max model length from the KV Cache budget

Choose a useful maximum request length that leaves enough cache for the number of active requests you want to serve.

Read guide →

vLLM concurrency

Plan vLLM concurrency before raising max_num_seqs

Translate a request target into cache pressure before exposing it as an endpoint concurrency limit.

Read guide →

LoRA mode

Choose LoRA or QLoRA from the base-weight budget

Choose the adapter path only after you know how much of the GPU is already occupied by the frozen base model.

Read guide →

Training memory

Set sequence length and micro-batch before increasing VRAM

Control activation memory with the two workload inputs that move it most: sequence length and micro-batch size.

Read guide →