# Longhaul MoE loading

Longhaul mode keeps the non-expert model weights resident and loads routed MoE expert slices from the GGUF file as they are needed. The expert cache has a fixed budget and uses least-recently-used replacement independently for each layer.

This mode is intended for running a model whose full expert weights do not fit in unified memory. It trades throughput and latency for a smaller resident model allocation.

## Usage

```sh
llama-cli \
    --model /path/to/model.gguf \
    --longhaul \
    --longhaul-cache 2 \
    --n-gpu-layers 0
```

`--longhaul-cache` is the expert cache budget in GiB. It is required when `--longhaul` is used. The same options are accepted by `llama-server`.

The command above runs every repeating layer on CPU and is supported on macOS,
Linux, and Windows. On macOS, the existing all-Metal mode remains available by
using `--n-gpu-layers 99` instead. Longhaul does not silently change device
placement: an unsupported GPU or mixed CPU/GPU repeating-layer placement fails
with guidance to use `--n-gpu-layers 0`.

Longhaul may reduce `--ubatch-size` so that every expert selected by one graph segment can be present in the cache at the same time. The effective value is logged during context creation. If one token selects more experts than the cache has slots, the routed MoE computation is split into multiple stages and the partial results are summed. This permits smaller caches at the cost of additional graph work.

The normal startup warmup is skipped automatically in longhaul mode. Routed expert weights are not read until the first real decode.

## Current scope

Longhaul currently requires:

- all repeating layers on CPU, or all repeating layers on Metal
- Qwen3.5 MoE, Laguna, or Inkling architecture
- text generation without embeddings or LoRA adapters

CPU mode is available wherever the CPU backend is supported. Metal mode requires
macOS. Longhaul does not restrict the GGUF quantization type; individual tensor
types must still be supported by the selected compute backend.

MTP/speculative decoding, tensor validation during loading, vocabulary-only
loading, and mixed CPU/GPU repeating-layer placement are not supported. Both
single-file and split GGUF models are supported; routed expert tensors are read
from the shard that owns each tensor.

The cache budget covers the compact routed-expert tensors. It does not include
dense weights, attention weights, the KV cache, graph allocations, or temporary
staging buffers. CPU expert caches use the standard directly writable tensor
layout so individual slots can be replaced; optimized CPU buffer selection
continues to apply to all non-streamed weights.

File-cache control is best effort and is outside the explicit cache budget.
macOS disables caching for streamed files where supported, and Linux advises the
kernel to discard completed reads. Windows may retain file data in its system
cache. Windows reads from one GGUF shard are serialized to preserve positional
read correctness, while POSIX systems retain concurrent `pread` operations.

This implementation synchronizes at each routed MoE layer to discover the selected experts, populate missing cache slots, and continue execution with cache-local expert IDs. Storage speed and expert reuse therefore have a large effect on generation speed.

Expert IDs are planned as a batch at each synchronization point. Experts already
needed by that batch are protected from eviction, duplicate IDs are loaded only
once, and independent expert slices are read concurrently where the platform
supports positional reads. CPU and shared Metal buffers are populated directly;
private Metal buffers use a staged fallback.

Inkling keeps its two shared experts resident and streams only the routed
256-expert banks. Inkling-Small selects six routed experts per token. For the
current three-shard UD-IQ1_S model, a 2 GiB cache provides seven routed-expert
slots and therefore executes each MoE layer in one stage:

```sh
llama-cli \
    --model /path/to/Inkling-Small-UD-IQ1_S-00001-of-00003.gguf \
    --longhaul \
    --longhaul-cache 2
```

Add `--n-gpu-layers 0` to run entirely on CPU; on macOS the default all-Metal
placement is supported.

## Benchmarking prompt processing

`llama-bench` accepts the longhaul load mode and cache budget:

```sh
llama-bench \
    --model /path/to/model.gguf \
    --load-mode longhaul \
    --longhaul-cache 2 \
    --n-gpu-layers 0 \
    --n-prompt 2048 \
    --n-gen 0
```

Use `--no-warmup --repetitions 1` in separate processes to measure a cold expert
cache. Leave warmup enabled to measure steady-state cache reuse.