Measure speculative decoding: all ngram modes lose to plain decoding

Verifying a K-token draft costs ~K times the CPU expert work, because each
token routes to its own 8-of-256 experts and nothing is amortized. The loss
is largest on structured code output (-51% for ngram-simple), i.e. exactly
where speculation should have won.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

README.md

@@ -113,12 +113,36 @@ Generation falls off ~40% between empty and ~97k, which is the attention cost on
 10 full-attention layers. Prefill stays flat around 420–490 t/s, so filling the whole
 128k window takes roughly 4–5 minutes.
 
-### 5. Rejected
+### 5. Speculative decoding makes it slower — don't enable it
+
+Counter-intuitive but consistent, `--n-predict 400`, thinking disabled:
+
+| workload | none | ngram-mod | ngram-simple | ngram-cache |
+|---|---|---|---|---|
+| rewrite (output ≈ copy of prompt) | **55.6** | 40.6 | 39.7 | 47.0 |
+| extend (structured code) | **55.3** | 32.7 | 27.2 | 38.1 |
+| prose (novel text, control) | **56.1** | 54.7 | 52.9 | 48.4 |
+
+Every mode loses, and it loses *most* on exactly the structured workloads
+speculation is supposed to win. The reason is the CPU-side experts: verifying a
+K-token draft costs about K times the CPU expert work, because each token routes to
+its own subset of 8 out of 256 experts, so there is no weight reuse to amortize.
+On a fully GPU-resident model batch verification is nearly free; with
+`--n-cpu-moe` it is not. Reconsider only if the model ever fits entirely in VRAM.
+
+### 6. Rejected
 
 - `-ub 256`: frees only ~80 MiB per GPU (not the 469 MiB an extra layer needs) and
   costs **38% prefill** (556 → 347 t/s). Keep the default `-ub 512`.
 - Lower `-ts` toward CUDA1 (e.g. `23,17`): would leave CUDA1 at ~60 MiB free.
 
+### A note on the CUDA0 headroom
+
+Free VRAM on CUDA0 was observed drifting between ~1100 and ~1300 MiB across restarts
+purely from desktop compositor churn — a ~200 MiB swing with nothing else changing.
+That is why the default keeps >1 GiB spare there rather than the 388 MiB that
+`ncmoe=8` leaves.
+
 ## Deploy
 
 ```bash
@@ -133,6 +157,7 @@ Loads in ~15 s (`--no-mmap`, weights read from NVMe).
 ```bash
 python3 bench/bench.py --port 18008 --depths 512,8192,32768 --n-predict 128
 ./bench/sweep.sh 10:24,16:8 8:24,16:8      # <ncmoe>:<tensor-split>:<threads>
+python3 bench/spec_bench.py --no-think     # copy/code/prose generation workloads
 ```
 
 `bench.py` issues a warmup request first — without it the first measurement reads