docs: serving profiles with KV pool / concurrency numbers

README.md

@@ -35,8 +35,17 @@ To switch back to the INT8 embedding: restore the original
 `model-00002-of-00005.safetensors` + `config.json` from the main repo (keep a copy before
 overwriting, or re-download it).
 
-Serving is as in the main repo's README: the [HyperQwen](https://github.com/syv-ai/HyperQwen)
-vLLM fork single-user launcher (`CTX=long` profile, ~220K-token KV pool).
+## Serve
+
+Serve the swapped model (e.g. a directory named `model-fast-emb4`) with the
+[HyperQwen](https://github.com/syv-ai/HyperQwen) vLLM fork single-user launcher:
+
+```bash
+MODEL=path/to/model-fast-emb4 PREFIX_CACHE=1 VISION=1 SPEC=mtp CTX=long REQ_METRICS=1 bash single-user/start_qwen.sh
+```
+
+GPU KV cache size: **218,112 tokens** — maximum concurrency for 150,000 tokens per request:
+**1.45x** (the INT4 embedding frees ~0.6 GB back to the KV pool vs the INT8 version).
 
 ## License