progress

docs/longhaul.md

@@ -31,7 +31,7 @@ The normal startup warmup is skipped automatically in longhaul mode. Routed expe
 Longhaul currently requires:
 
 - all repeating layers on CPU, or all repeating layers on Metal
-- Qwen3.5 MoE or Laguna architecture
+- 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
@@ -63,6 +63,21 @@ 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: