Multiple GPUs support: migrate the code from ChatGLM-6B, make a few modifications to support ChatGLM2.

Author: qinjx

cli_demo.py

@@ -3,9 +3,14 @@
 import signal
 from transformers import AutoTokenizer, AutoModel
 import readline
+from utils import load_model_on_gpus
 
 tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
 model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, device='cuda')
+# 多显卡支持，注释掉下面三行，将num_gpus改为你实际的显卡数量
+# model_path = "THUDM/chatglm2-6b"
+# tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+# model = load_model_on_gpus(model_path, num_gpus=2)
 model = model.eval()
 
 os_name = platform.system()

utils.py

@@ -0,0 +1,59 @@
+import os
+from typing import Dict, Tuple, Union, Optional
+
+from torch.nn import Module
+from transformers import AutoModel
+
+
+def auto_configure_device_map(num_gpus: int) -> Dict[str, int]:
+    # transformer.word_embeddings 占用1层
+    # transformer.final_layernorm 和 lm_head 占用1层
+    # transformer.layers 占用 28 层
+    # 总共30层分配到num_gpus张卡上
+    num_trans_layers = 28
+    per_gpu_layers = 30 / num_gpus
+
+    # bugfix: 在linux中调用torch.embedding传入的weight,input不在同一device上,导致RuntimeError
+    # windows下 model.device 会被设置成 transformer.word_embeddings.device
+    # linux下 model.device 会被设置成 lm_head.device
+    # 在调用chat或者stream_chat时,input_ids会被放到model.device上
+    # 如果transformer.word_embeddings.device和model.device不同,则会导致RuntimeError
+    # 因此这里将transformer.word_embeddings,transformer.final_layernorm,lm_head都放到第一张卡上
+    # 本文件来源于https://github.com/THUDM/ChatGLM-6B/blob/main/utils.py
+    # 仅此处做少许修改以支持ChatGLM2
+    device_map = {
+        'transformer.embedding.word_embeddings': 0,
+        'transformer.encoder.final_layernorm': 0,
+        'transformer.output_layer': 0,
+        'transformer.rotary_pos_emb': 0,
+        'lm_head': 0
+    }
+
+    used = 2
+    gpu_target = 0
+    for i in range(num_trans_layers):
+        if used >= per_gpu_layers:
+            gpu_target += 1
+            used = 0
+        assert gpu_target < num_gpus
+        device_map[f'transformer.encoder.layers.{i}'] = gpu_target
+        used += 1
+
+    return device_map
+
+
+def load_model_on_gpus(checkpoint_path: Union[str, os.PathLike], num_gpus: int = 2,
+                       device_map: Optional[Dict[str, int]] = None, **kwargs) -> Module:
+    if num_gpus < 2 and device_map is None:
+        model = AutoModel.from_pretrained(checkpoint_path, trust_remote_code=True, **kwargs).half().cuda()
+    else:
+        from accelerate import dispatch_model
+
+        model = AutoModel.from_pretrained(checkpoint_path, trust_remote_code=True, **kwargs).half()
+
+        if device_map is None:
+            device_map = auto_configure_device_map(num_gpus)
+
+        model = dispatch_model(model, device_map=device_map)
+
+    return model

web_demo.py

@@ -4,6 +4,10 @@
 
 tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
 model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, device='cuda')
+# 多显卡支持，注释掉下面三行，将num_gpus改为你实际的显卡数量
+# model_path = "THUDM/chatglm2-6b"
+# tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+# model = load_model_on_gpus(model_path, num_gpus=2)
 model = model.eval()
 
 """Override Chatbot.postprocess"""