forked from meta-llama/llama
-
Notifications
You must be signed in to change notification settings - Fork 0
/
api.py
148 lines (120 loc) · 4.16 KB
/
api.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# coding: utf-8
# Copy From https://github.com/facebookresearch/llama/blob/797488b96795c50ed79276b3aeab8f1436518301/server.py
from typing import Tuple
import os
import sys
import argparse
import torch
import time
import json
from pathlib import Path
from typing import List
from pydantic import BaseModel
from fastapi import FastAPI
import uvicorn
import torch.distributed as dist
from fairscale.nn.model_parallel.initialize import initialize_model_parallel
from llama import ModelArgs, Transformer, Tokenizer, LLaMA
parser = argparse.ArgumentParser()
parser.add_argument("--max_seq_len", type=int, default=512)
parser.add_argument("--max_batch_size", type=int, default=32)
app = FastAPI()
def setup_model_parallel() -> Tuple[int, int]:
local_rank = int(os.environ.get("LOCAL_RANK", -1))
world_size = int(os.environ.get("WORLD_SIZE", -1))
dist.init_process_group("nccl")
initialize_model_parallel(world_size)
torch.cuda.set_device(local_rank)
# seed must be the same in all processes
torch.manual_seed(1)
return local_rank, world_size
def load(
ckpt_dir: str,
tokenizer_path: str,
local_rank: int,
world_size: int,
max_seq_len: int,
max_batch_size: int,
) -> LLaMA:
start_time = time.time()
checkpoints = sorted(Path(ckpt_dir).glob("*.pth"))
# assert world_size == len(
# checkpoints
# ), f"Loading a checkpoint for MP={len(checkpoints)} but world size is {world_size}"
ckpt_path = checkpoints[local_rank]
print("Loading")
checkpoint = torch.load(ckpt_path, map_location="cpu")
with open(Path(ckpt_dir) / "params.json", "r") as f:
params = json.loads(f.read())
model_args: ModelArgs = ModelArgs(
max_seq_len=max_seq_len, max_batch_size=max_batch_size, **params
)
tokenizer = Tokenizer(model_path=tokenizer_path)
model_args.vocab_size = tokenizer.n_words
torch.set_default_tensor_type(torch.cuda.HalfTensor)
model = Transformer(model_args)
torch.set_default_tensor_type(torch.FloatTensor)
model.load_state_dict(checkpoint, strict=False)
generator = LLaMA(model, tokenizer)
print(f"Loaded in {time.time() - start_time:.2f} seconds")
return generator
def init_generator(
ckpt_dir: str,
tokenizer_path: str,
max_seq_len: int = 512,
max_batch_size: int = 32,
):
local_rank, world_size = setup_model_parallel()
if local_rank > 0:
sys.stdout = open(os.devnull, "w")
generator = load(
ckpt_dir, tokenizer_path, local_rank, world_size, max_seq_len, max_batch_size
)
return generator
if __name__ == "__main__":
args = parser.parse_args()
generator = init_generator(
"ckpts/7B_fs/",
"ckpts/tokenizer.model",
args.max_seq_len,
args.max_batch_size,
)
class Config(BaseModel):
prompts: List[str]
max_gen_len: int
temperature: float = 0.8
top_p: float = 0.95
if dist.get_rank() == 0:
@app.post("/llama/")
def generate(config: Config):
if len(config.prompts) > args.max_batch_size:
return {"error": "too much prompts."}
for prompt in config.prompts:
if len(prompt) + config.max_gen_len > args.max_seq_len:
return {"error": "max_gen_len too large."}
dist.broadcast_object_list(
[config.prompts, config.max_gen_len, config.temperature, config.top_p]
)
results = generator.generate(
config.prompts,
max_gen_len=config.max_gen_len,
temperature=config.temperature,
top_p=config.top_p,
)
return {
"results": [{"text": x.text, "token_ids_lst": x.token} for x in results]
}
uvicorn.run(app, host="0.0.0.0", port=6006)
else:
while True:
config = [None] * 4
try:
dist.broadcast_object_list(config)
generator.generate(
config[0],
max_gen_len=config[1],
temperature=config[2],
top_p=config[3],
)
except:
pass