Upload README.md with huggingface_hub

README.md

@@ -77,7 +77,7 @@ cmake --build build --target llama-cli llama-server
 llama-server -m Qwen3.6-27B-Q5_K_M-mtp.gguf \
   --spec-type mtp --spec-draft-n-max 5 \
   --cache-type-k q4_0 --cache-type-v q4_0 \
-  -c 262144 --temp 0.7 --top-k 20 -ngl 99 --port 8081
+  -np 1 -c 262144 --temp 0.7 --top-k 20 -ngl 99 --port 8081
 ```
 
 That's it. Three optimizations in one command:
@@ -227,7 +227,7 @@ curl http://localhost:8081/v1/messages \
 llama-cli -m Qwen3.6-27B-Q5_K_M-mtp.gguf \
   --spec-type mtp --spec-draft-n-max 5 \
   --cache-type-k q8_0 --cache-type-v q8_0 \
-  -c 4096 -n 2048 --temp 0.7 -ngl 99 \
+  -np 1 -c 4096 -n 2048 --temp 0.7 -ngl 99 \
   -p "Your prompt here"
 
 # Vision (MTP does not work with images — omit --spec-type mtp)
@@ -270,9 +270,11 @@ Effect on hardware requirements (Q5_K_M, 80K context):
 The model predicts 5 extra tokens per step using its own MTP heads, then verifies them in one pass. No extra model needed.
 
 ```bash
---spec-type mtp --spec-draft-n-max 5
+--spec-type mtp --spec-draft-n-max 5 -np 1
 ```
 
+MTP currently requires `-np 1` (single-sequence mode). Without it, you'll get: `MTP currently supports only n_parallel=1`.
+
 Tune `--spec-draft-n-max`: **5** for general use, **8–10** for code, **3** for creative writing.
 
 ### Draft model (~2.3x faster)