推理场景介绍

方案概览

本方案介绍了在ModelArts的Lite k8s Cluster上使用昇腾计算资源开展常见开源大模型Llama、Qwen、ChatGLM、Yi、Baichuan等推理部署的详细过程。本方案利用适配昇腾平台的大模型推理服务框架vLLM和华为自研昇腾Snt9B硬件，为用户提供推理部署方案，帮助用户使能大模型业务。

约束限制

本方案目前仅适用于部分企业客户。
本文档适配昇腾云ModelArts 6.3.910版本，请参考软件配套版本获取配套版本的软件包，请严格遵照版本配套关系使用本文档。
资源规格推荐使用“西南-贵阳一”Region上的Lite k8s Cluster和昇腾Snt9B资源。
本文档中的CCE集群版本选择v1.27~1.28。版本使用的容器引擎为Containerd。
推理部署使用的服务框架是vLLM。vLLM支持v0.6.0版本。
支持FP16和BF16数据类型推理。
Lite k8s Cluster驱动版本推荐为23.0.6。
适配的CANN版本是cann_8.0.rc3。

资源规格要求

本文档中的模型运行环境是ModelArts Lite的Lite k8s Cluster。推荐使用“西南-贵阳一”Region上的资源和Ascend Snt9B。

支持的模型列表和权重文件

本方案支持vLLM的v0.6.0版本。不同vLLM版本支持的模型列表有差异，具体如表1所示。

表1 支持的模型列表和权重获取地址
序号	模型名称	是否支持fp16/bf16推理	是否支持W4A16量化	是否支持W8A8量化	是否支持W8A16量化	是否支持 kv-cache-int8量化	开源权重获取地址
1	llama-7b	√	√	√	√	√	https://huggingface.co/huggyllama/llama-7b
2	llama-13b	√	√	√	√	√	https://huggingface.co/huggyllama/llama-13b
3	llama-65b	√	√	√	√	√	https://huggingface.co/huggyllama/llama-65b
4	llama2-7b	√	√	√	√	√	https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
5	llama2-13b	√	√	√	√	√	https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
6	llama2-70b	√	√	√	√	√	https://huggingface.co/meta-llama/Llama-2-70b-hf https://huggingface.co/meta-llama/Llama-2-70b-chat-hf (推荐)
7	llama3-8b	√	√	√	√	√	https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
8	llama3-70b	√	√	√	√	√	https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct
9	yi-6b	√	√	√	√	√	https://huggingface.co/01-ai/Yi-6B-Chat
10	yi-9b	√	√	√	√	√	https://huggingface.co/01-ai/Yi-9B
11	yi-34b	√	√	√	√	√	https://huggingface.co/01-ai/Yi-34B-Chat
12	deepseek-llm-7b	√	x	x	x	x	https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat
13	deepseek-coder-33b-instruct	√	x	x	x	x	https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct
14	deepseek-llm-67b	√	x	x	x	x	https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
15	qwen-7b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen-7B-Chat
16	qwen-14b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen-14B-Chat
17	qwen-72b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen-72B-Chat
18	qwen1.5-0.5b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat
19	qwen1.5-7b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen1.5-7B-Chat
20	qwen1.5-1.8b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat
21	qwen1.5-14b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen1.5-14B-Chat
22	qwen1.5-32b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen1.5-32B/tree/main
23	qwen1.5-72b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen1.5-72B-Chat
24	qwen1.5-110b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen1.5-110B-Chat
25	qwen2-0.5b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2-0.5B-Instruct
26	qwen2-1.5b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2-1.5B-Instruct
27	qwen2-7b	√	√	x	√	x	https://huggingface.co/Qwen/Qwen2-7B-Instruct
28	qwen2-72b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2-72B-Instruct
29	qwen2.5-0.5b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct
30	qwen2.5-1.5b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct
31	qwen2.5-3b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2.5-3B-Instruct
32	qwen2.5-7b	√	√	x	√	x	https://huggingface.co/Qwen/Qwen2.5-7B-Instruct
33	qwen2.5-14b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2.5-14B-Instruct
34	qwen2.5-32b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2.5-32B-Instruct
35	qwen2.5-72b	√	√	√	√	x	https://huggingface.co/Qwen/Qwen2.5-72B-Instruct
36	baichuan2-7b	√	x	x	√	x	https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat
37	baichuan2-13b	√	x	x	√	x	https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat
38	gemma-2b	√	x	x	x	x	https://huggingface.co/google/gemma-2b
39	gemma-7b	√	x	x	x	x	https://huggingface.co/google/gemma-7b
40	chatglm2-6b	√	x	x	x	x	https://huggingface.co/THUDM/chatglm2-6b
41	chatglm3-6b	√	x	x	x	x	https://huggingface.co/THUDM/chatglm3-6b
42	glm-4-9b	√	x	x	x	x	https://huggingface.co/THUDM/glm-4-9b-chat
43	mistral-7b	√	x	x	x	x	https://huggingface.co/mistralai/Mistral-7B-v0.1
44	mixtral-8x7b	√	x	x	x	x	https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
45	falcon-11b	√	x	x	x	x	https://huggingface.co/tiiuae/falcon-11B/tree/main
46	qwen2-57b-a14b	√	x	x	x	x	https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct
47	llama3.1-8b	√	√	√	√	x	https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
48	llama3.1-70b	√	√	√	√	x	https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct
49	llama-3.1-405B	√	√	x	x	x	https://huggingface.co/hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4
50	llama-3.2-1B	√	x	x	x	x	Llama-3.2-1B-Instruct · 模型库 (modelscope.cn)
51	llama-3.2-3B	√	x	x	x	x	Llama-3.2-3B-Instruct · 模型库 (modelscope.cn)
52	llava-1.5-7b	√	x	x	x	x	https://huggingface.co/llava-hf/llava-1.5-7b-hf/tree/main
53	llava-1.5-13b	√	x	x	x	x	https://huggingface.co/llava-hf/llava-1.5-13b-hf/tree/main
54	llava-v1.6-7b	√	x	x	x	x	https://huggingface.co/llava-hf/llava-v1.6-vicuna-7b-hf/tree/main
55	llava-v1.6-13b	√	x	x	x	x	https://huggingface.co/llava-hf/llava-v1.6-vicuna-13b-hf/tree/main
56	llava-v1.6-34b	√	x	x	x	x	llava-hf/llava-v1.6-34b-hf at main (huggingface.co)
57	internvl2-8B	√	x	x	x	x	OpenGVLab/InternVL2-8B at main (huggingface.co)
58	internvl2-26B	√	x	x	x	x	OpenGVLab/InternVL2-26B at main (huggingface.co)
59	internvl2-40B	√	x	x	x	x	OpenGVLab/InternVL2-40B at main (huggingface.co)
60	MiniCPM-v2.6	√	x	x	x	x	https://huggingface.co/openbmb/MiniCPM-V-2_6/tree/main
61	deepseek-v2-236b	x	x	√	x	x	https://huggingface.co/deepseek-ai/DeepSeek-V2
62	deepseek-v2-lite-16b	√	x	√	x	x	https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite
63	qwen2-vl-7B	√	x	x	x	x	Qwen/Qwen2-VL-7B-Instruct at main (huggingface.co) 注意：Qwen2-VL 开源vllm依赖特定transformers版本，请手动安装： pip install git+https://github.com/huggingface/transformers.git@21fac7abba2a37fae86106f87fcf9974fd1e3830
64	qwen-vl	√	x	x	x	x	https://huggingface.co/Qwen/Qwen-VL
65	qwen-vl-chat	√	x	x	x	x	https://huggingface.co/Qwen/Qwen-VL-Chat
66	MiniCPM-v2	√	x	x	x	x	https://huggingface.co/HwwwH/MiniCPM-V-2 注意：需要修改源文件site-packages/timm/layers/pos_embed.py，在第46行上面新增一行代码，如下： posemb = posemb.contiguous() #新增 posemb = F.interpolate(posemb, size=new_size, mode=interpolation, antialias=antialias)