Merge branch 'vllm-project:main' into main

Author: haojiangzheng

.github/workflows/vllm_ascend_test.yaml

@@ -278,6 +278,7 @@ jobs:
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_dbo
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeekV3_dbo
+          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_alltoallv
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC
           pytest -sv tests/e2e/multicard/test_data_parallel.py
           pytest -sv tests/e2e/multicard/ --ignore=tests/e2e/multicard/test_ilama_lora_tp2.py \

.github/workflows/vllm_ascend_test_310p.yaml

@@ -58,7 +58,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     container:
       # TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-310p-ubuntu22.04-py3.10
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-310p-ubuntu22.04-py3.11
       env:
         VLLM_LOGGING_LEVEL: ERROR
         VLLM_USE_MODELSCOPE: True

docs/source/tutorials/single_node_300i.md

@@ -1,7 +1,8 @@
 # Single Node (Atlas 300I series)
 
 ```{note}
-This Atlas 300I series is currently experimental. In future versions, there may be behavioral changes around model coverage, performance improvement.
+1. This Atlas 300I series is currently experimental. In future versions, there may be behavioral changes around model coverage, performance improvement.
+2. Currently, the 310I series only supports eager mode and the data type is float16.
 ```
 
 ## Run vLLM on Altlas 300I series
@@ -83,7 +84,7 @@ curl http://localhost:8000/v1/completions \
 
 ::::
 
-::::{tab-item} Qwen/Qwen2.5-7B-Instruct
+::::{tab-item} Qwen2.5-7B-Instruct
 :sync: qwen7b
 
 Run the following command to start the vLLM server:
@@ -113,6 +114,36 @@ curl http://localhost:8000/v1/completions \
 
 ::::
 
+::::{tab-item} Qwen2.5-VL-3B-Instruct
+:sync: qwen-vl-2.5-3b
+
+Run the following command to start the vLLM server:
+
+```{code-block} bash
+   :substitutions:
+vllm serve Qwen/Qwen2.5-VL-3B-Instruct \
+    --tensor-parallel-size 1 \
+    --enforce-eager \
+    --dtype float16 \
+    --compilation-config '{"custom_ops":["none", "+rms_norm", "+rotary_embedding"]}'
+```
+
+Once your server is started, you can query the model with input prompts
+
+```bash
+curl http://localhost:8000/v1/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "prompt": "The future of AI is",
+    "max_tokens": 64,
+    "top_p": 0.95,
+    "top_k": 50,
+    "temperature": 0.6
+  }'
+```
+
+::::
+
 ::::{tab-item} Pangu-Pro-MoE-72B
 :sync: pangu
 
@@ -251,6 +282,49 @@ clean_up()
 
 ::::
 
+::::{tab-item} Qwen2.5-VL-3B-Instruct
+:sync: qwen-vl-2.5-3b
+
+```{code-block} python
+   :substitutions:
+from vllm import LLM, SamplingParams
+import gc
+import torch
+from vllm import LLM, SamplingParams
+from vllm.distributed.parallel_state import (destroy_distributed_environment,
+                                             destroy_model_parallel)
+
+def clean_up():
+    destroy_model_parallel()
+    destroy_distributed_environment()
+    gc.collect()
+    torch.npu.empty_cache()
+prompts = [
+    "Hello, my name is",
+    "The future of AI is",
+]
+# Create a sampling params object.
+sampling_params = SamplingParams(max_tokens=100, top_p=0.95, top_k=50, temperature=0.6)
+# Create an LLM.
+llm = LLM(
+    model="Qwen/Qwen2.5-VL-3B-Instruct",
+    tensor_parallel_size=1,
+    enforce_eager=True, # For 300I series, only eager mode is supported.
+    dtype="float16", # IMPORTANT cause some ATB ops cannot support bf16 on 300I series
+    compilation_config={"custom_ops":["none", "+rms_norm", "+rotary_embedding"]}, # High performance for 300I series
+)
+# Generate texts from the prompts.
+outputs = llm.generate(prompts, sampling_params)
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+del llm
+clean_up()
+```
+
+::::
+
 ::::{tab-item} Pangu-Pro-MoE-72B
 :sync: pangu