This repository was archived by the owner on Oct 11, 2024. It is now read-only.
forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 10
/
Copy pathbackend_request_func.py
356 lines (303 loc) · 12.1 KB
/
backend_request_func.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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
# This file has been modified by Neural Magic
import json
import os
import time
from dataclasses import dataclass
from typing import Optional
import aiohttp
from tqdm.asyncio import tqdm
AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=6 * 60 * 60)
@dataclass
class RequestFuncInput:
prompt: str
api_url: str
prompt_len: int
output_len: int
model: str
best_of: int = 1
use_beam_search: bool = False
@dataclass
class RequestFuncOutput:
generated_text: str = ""
success: bool = False
latency: float = 0
ttft: float = 0
prompt_len: int = 0
async def async_request_tgi(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
api_url = request_func_input.api_url
assert api_url.endswith("generate_stream")
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
assert not request_func_input.use_beam_search
params = {
"best_of": request_func_input.best_of,
"max_new_tokens": request_func_input.output_len,
"do_sample": True,
"temperature": 0.01, # TGI does not accept 0.0 temperature.
"top_p": 0.99, # TGI does not accept 1.0 top_p.
}
payload = {
"inputs": request_func_input.prompt,
"parameters": params,
}
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
ttft = 0
st = time.perf_counter()
try:
async with session.post(url=api_url, json=payload) as response:
if response.status == 200:
async for data in response.content.iter_any(): # noqa
if ttft == 0:
ttft = time.perf_counter() - st
output.ttft = ttft
output.latency = time.perf_counter() - st
body = data.decode("utf-8").lstrip("data:") # noqa
output.generated_text = json.loads(body)["generated_text"]
output.success = True
else:
output.success = False
except (aiohttp.ClientOSError, aiohttp.ServerDisconnectedError):
output.success = False
if pbar:
pbar.update(1)
return output
async def async_request_vllm(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
api_url = request_func_input.api_url
assert api_url.endswith("generate")
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
payload = {
"prompt": request_func_input.prompt,
"n": 1,
"best_of": request_func_input.best_of,
"use_beam_search": request_func_input.use_beam_search,
"temperature": 0.0 if request_func_input.use_beam_search else 1.0,
"top_p": 1.0,
"max_tokens": request_func_input.output_len,
"ignore_eos": True,
"stream": True,
}
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
ttft = 0
st = time.perf_counter()
try:
async with session.post(url=api_url, json=payload) as response:
if response.status == 200:
async for data in response.content.iter_any(): # noqa
if ttft == 0:
ttft = time.perf_counter() - st
output.ttft = ttft
output.latency = time.perf_counter() - st
# When streaming, '\0' is appended to the end of the response.
body = data.decode("utf-8").strip("\0")
output.generated_text = json.loads(
body)["text"][0][len(request_func_input.prompt):]
output.success = True
else:
output.success = False
except (aiohttp.ClientOSError, aiohttp.ServerDisconnectedError):
output.success = False
if pbar:
pbar.update(1)
return output
async def async_request_trt_llm(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
api_url = request_func_input.api_url
assert api_url.endswith("generate_stream")
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
assert not request_func_input.use_beam_search
assert request_func_input.best_of == 1
payload = {
"accumulate_tokens": True,
"text_input": request_func_input.prompt,
"temperature": 0.0,
"top_p": 1.0,
"max_tokens": request_func_input.output_len,
"stream": True,
}
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
ttft = 0
st = time.perf_counter()
try:
async with session.post(url=api_url, json=payload) as resp:
if resp.status == 200:
async for data in resp.content.iter_any(): # noqa
if ttft == 0:
ttft = time.perf_counter() - st
output.ttft = ttft
output.latency = time.perf_counter() - st
body = data.decode("utf-8").lstrip("data:") # noqa
output.generated_text = json.loads(body)["text_output"]
output.success = True
else:
output.success = False
except (aiohttp.ClientOSError, aiohttp.ServerDisconnectedError):
output.success = False
if pbar:
pbar.update(1)
return output
async def async_request_deepspeed_mii(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
assert request_func_input.best_of == 1
assert not request_func_input.use_beam_search
payload = {
"prompts": request_func_input.prompt,
"max_new_tokens": request_func_input.output_len,
"ignore_eos": True,
"do_sample": True,
"temperature":
0.01, # deepspeed-mii does not accept 0.0 temperature.
"top_p": 1.0,
}
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
# DeepSpeed-MII doesn't support streaming as of Jan 28 2024, will use 0 as placeholder.
# https://github.com/microsoft/DeepSpeed-MII/pull/311
output.ttft = 0
st = time.perf_counter()
try:
async with session.post(url=request_func_input.api_url,
json=payload) as resp:
if resp.status == 200:
parsed_resp = await resp.json()
output.latency = time.perf_counter() - st
output.generated_text = parsed_resp[0]["generated_text"]
output.success = True
else:
output.success = False
except (aiohttp.ClientOSError, aiohttp.ServerDisconnectedError):
output.success = False
if pbar:
pbar.update(1)
return output
async def async_request_openai_completions(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
api_url = request_func_input.api_url
assert api_url.endswith("v1/completions")
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
assert not request_func_input.use_beam_search
payload = {
"model": request_func_input.model,
"prompt": request_func_input.prompt,
"temperature": 0.0,
"best_of": request_func_input.best_of,
"max_tokens": request_func_input.output_len,
"stream": True,
}
headers = {
"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"
}
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
generated_text = ""
ttft = 0
st = time.perf_counter()
try:
async with session.post(url=api_url, json=payload,
headers=headers) as response:
if response.status == 200:
async for chunk in response.content:
if ttft == 0:
ttft = time.perf_counter() - st
output.ttft = ttft
chunk = chunk.strip()
if not chunk:
continue
chunk = chunk.decode("utf-8").lstrip("data: ") # noqa
if chunk == "[DONE]":
latency = time.perf_counter() - st
else:
body = json.loads(chunk)
generated_text += body["choices"][0]["text"]
output.generated_text = generated_text
output.success = True
output.latency = latency
else:
output.success = False
except (aiohttp.ClientOSError, aiohttp.ServerDisconnectedError):
output.success = False
if pbar:
pbar.update(1)
return output
async def async_request_openai_chat_completions(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
api_url = request_func_input.api_url
assert api_url.endswith(
"v1/chat/completions"
), "OpenAI Chat API URL must end with 'v1/chat/completions'."
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
assert not request_func_input.use_beam_search
payload = {
"model": request_func_input.model,
"messages": [
{
"role": "user",
"content": request_func_input.prompt,
},
],
"temperature": 0.0,
"max_tokens": request_func_input.output_len,
"stream": True,
}
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"
}
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
generated_text = ""
ttft = 0
st = time.perf_counter()
try:
async with session.post(url=api_url, json=payload,
headers=headers) as response:
if response.status == 200:
async for chunk in response.content:
if ttft == 0:
ttft = time.perf_counter() - st
output.ttft = ttft
chunk = chunk.strip()
if not chunk:
continue
chunk = chunk.decode("utf-8").lstrip("data: ")
if chunk == "[DONE]":
latency = time.perf_counter() - st
else:
body = json.loads(chunk)
if "content" in body["choices"][0]["delta"]:
generated_text += body["choices"][0]["delta"][
"content"]
output.generated_text = generated_text
output.success = True
output.latency = latency
else:
output.success = False
except (aiohttp.ClientOSError, aiohttp.ServerDisconnectedError):
output.success = False
if pbar:
pbar.update(1)
return output
ASYNC_REQUEST_FUNCS = {
"tgi": async_request_tgi,
"vllm": async_request_vllm,
"deepspeed-mii": async_request_deepspeed_mii,
"openai": async_request_openai_completions,
"openai-chat": async_request_openai_chat_completions,
"tensorrt-llm": async_request_trt_llm,
}