Update README.md

README.md

@@ -1,3 +1,6 @@
+---
+license: apache-2.0
+---
 I used AutoAWQ to quantize Kimi K2
 
 vLLM seems to have a bug that prevents it from inferencing.
@@ -9,4 +12,21 @@ vLLM seems to have a bug that prevents it from inferencing.
 (VllmWorker rank=1 pid=644) ERROR 08-03 22:42:00 [multiproc_executor.py:511]     param[shard_offset:shard_offset + shard_size] = loaded_weight
 (VllmWorker rank=1 pid=644) ERROR 08-03 22:42:00 [multiproc_executor.py:511]     ~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 (VllmWorker rank=1 pid=644) ERROR 08-03 22:42:00 [multiproc_executor.py:511] RuntimeError: The expanded size of the tensor (264) must match the existing size (72) at non-singleton dimension 1.  Target sizes: [576, 264].  Tensor sizes: [7168, 72]
-```
+```
+
+I used AutoAWQ to quantize Kimi K2.
+
+Run with this command:
+
+```
+$ docker run -it --rm \
+  --gpus all \
+  --network=host \
+  --shm-size=1024g \
+  --entrypoint /bin/sh \
+  -v /home/hotaisle/workspace/models:/models \
+  -v $HOME/.cache/huggingface:/root/.cache/huggingface \
+  vllm/vllm-openai:latest \
+  -c "pip install blobfile && python3 -m vllm.entrypoints.openai.api_server --model QuixiAI/Kimi-K2-Base-AWQ --port 8000 --tensor-parallel-size 8 --trust-remote-code --gpu-memory-utilization 0.95 --enable-prefix-caching --enable-chunked-prefill --dtype bfloat16"```
+
+It seems due to a bug in vLLM, it cannot run.