guidellm 0.2.0rc20250421__tar.gz → 0.3.0rc6__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of guidellm might be problematic. Click here for more details.
- {guidellm-0.2.0rc20250421/src/guidellm.egg-info → guidellm-0.3.0rc6}/PKG-INFO +11 -207
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/README.md +1 -1
- guidellm-0.3.0rc6/pyproject.toml +238 -0
- guidellm-0.3.0rc6/setup.py +126 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/backend/openai.py +8 -1
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/benchmark/profile.py +0 -11
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/config.py +3 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/dataset/file.py +9 -7
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/request/loader.py +4 -1
- guidellm-0.3.0rc6/src/guidellm/version.py +6 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6/src/guidellm.egg-info}/PKG-INFO +11 -207
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm.egg-info/SOURCES.txt +2 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm.egg-info/requires.txt +3 -2
- guidellm-0.2.0rc20250421/pyproject.toml +0 -74
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/LICENSE +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/MANIFEST.in +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/setup.cfg +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/__main__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/backend/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/backend/backend.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/backend/response.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/benchmark/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/benchmark/aggregator.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/benchmark/benchmark.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/benchmark/benchmarker.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/benchmark/entrypoints.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/benchmark/output.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/benchmark/progress.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/data/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/data/prideandprejudice.txt.gz +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/dataset/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/dataset/creator.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/dataset/entrypoints.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/dataset/hf_datasets.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/dataset/in_memory.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/dataset/synthetic.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/logger.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/objects/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/objects/pydantic.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/objects/statistics.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/request/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/request/request.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/scheduler/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/scheduler/result.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/scheduler/scheduler.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/scheduler/strategy.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/scheduler/types.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/scheduler/worker.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/utils/__init__.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/utils/colors.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/utils/hf_transformers.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/utils/random.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm/utils/text.py +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm.egg-info/dependency_links.txt +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm.egg-info/entry_points.txt +0 -0
- {guidellm-0.2.0rc20250421 → guidellm-0.3.0rc6}/src/guidellm.egg-info/top_level.txt +0 -0
|
@@ -1,211 +1,14 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: guidellm
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.3.0rc6
|
|
4
4
|
Summary: Guidance platform for deploying and managing large language models.
|
|
5
|
-
Author:
|
|
6
|
-
License:
|
|
7
|
-
Version 2.0, January 2004
|
|
8
|
-
http://www.apache.org/licenses/
|
|
9
|
-
|
|
10
|
-
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
11
|
-
|
|
12
|
-
1. Definitions.
|
|
13
|
-
|
|
14
|
-
"License" shall mean the terms and conditions for use, reproduction,
|
|
15
|
-
and distribution as defined by Sections 1 through 9 of this document.
|
|
16
|
-
|
|
17
|
-
"Licensor" shall mean the copyright owner or entity authorized by
|
|
18
|
-
the copyright owner that is granting the License.
|
|
19
|
-
|
|
20
|
-
"Legal Entity" shall mean the union of the acting entity and all
|
|
21
|
-
other entities that control, are controlled by, or are under common
|
|
22
|
-
control with that entity. For the purposes of this definition,
|
|
23
|
-
"control" means (i) the power, direct or indirect, to cause the
|
|
24
|
-
direction or management of such entity, whether by contract or
|
|
25
|
-
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
26
|
-
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
27
|
-
|
|
28
|
-
"You" (or "Your") shall mean an individual or Legal Entity
|
|
29
|
-
exercising permissions granted by this License.
|
|
30
|
-
|
|
31
|
-
"Source" form shall mean the preferred form for making modifications,
|
|
32
|
-
including but not limited to software source code, documentation
|
|
33
|
-
source, and configuration files.
|
|
34
|
-
|
|
35
|
-
"Object" form shall mean any form resulting from mechanical
|
|
36
|
-
transformation or translation of a Source form, including but
|
|
37
|
-
not limited to compiled object code, generated documentation,
|
|
38
|
-
and conversions to other media types.
|
|
39
|
-
|
|
40
|
-
"Work" shall mean the work of authorship, whether in Source or
|
|
41
|
-
Object form, made available under the License, as indicated by a
|
|
42
|
-
copyright notice that is included in or attached to the work
|
|
43
|
-
(an example is provided in the Appendix below).
|
|
44
|
-
|
|
45
|
-
"Derivative Works" shall mean any work, whether in Source or Object
|
|
46
|
-
form, that is based on (or derived from) the Work and for which the
|
|
47
|
-
editorial revisions, annotations, elaborations, or other modifications
|
|
48
|
-
represent, as a whole, an original work of authorship. For the purposes
|
|
49
|
-
of this License, Derivative Works shall not include works that remain
|
|
50
|
-
separable from, or merely link (or bind by name) to the interfaces of,
|
|
51
|
-
the Work and Derivative Works thereof.
|
|
52
|
-
|
|
53
|
-
"Contribution" shall mean any work of authorship, including
|
|
54
|
-
the original version of the Work and any modifications or additions
|
|
55
|
-
to that Work or Derivative Works thereof, that is intentionally
|
|
56
|
-
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
57
|
-
or by an individual or Legal Entity authorized to submit on behalf of
|
|
58
|
-
the copyright owner. For the purposes of this definition, "submitted"
|
|
59
|
-
means any form of electronic, verbal, or written communication sent
|
|
60
|
-
to the Licensor or its representatives, including but not limited to
|
|
61
|
-
communication on electronic mailing lists, source code control systems,
|
|
62
|
-
and issue tracking systems that are managed by, or on behalf of, the
|
|
63
|
-
Licensor for the purpose of discussing and improving the Work, but
|
|
64
|
-
excluding communication that is conspicuously marked or otherwise
|
|
65
|
-
designated in writing by the copyright owner as "Not a Contribution."
|
|
66
|
-
|
|
67
|
-
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
68
|
-
on behalf of whom a Contribution has been received by Licensor and
|
|
69
|
-
subsequently incorporated within the Work.
|
|
70
|
-
|
|
71
|
-
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
72
|
-
this License, each Contributor hereby grants to You a perpetual,
|
|
73
|
-
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
74
|
-
copyright license to reproduce, prepare Derivative Works of,
|
|
75
|
-
publicly display, publicly perform, sublicense, and distribute the
|
|
76
|
-
Work and such Derivative Works in Source or Object form.
|
|
77
|
-
|
|
78
|
-
3. Grant of Patent License. Subject to the terms and conditions of
|
|
79
|
-
this License, each Contributor hereby grants to You a perpetual,
|
|
80
|
-
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
81
|
-
(except as stated in this section) patent license to make, have made,
|
|
82
|
-
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
83
|
-
where such license applies only to those patent claims licensable
|
|
84
|
-
by such Contributor that are necessarily infringed by their
|
|
85
|
-
Contribution(s) alone or by combination of their Contribution(s)
|
|
86
|
-
with the Work to which such Contribution(s) was submitted. If You
|
|
87
|
-
institute patent litigation against any entity (including a
|
|
88
|
-
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
89
|
-
or a Contribution incorporated within the Work constitutes direct
|
|
90
|
-
or contributory patent infringement, then any patent licenses
|
|
91
|
-
granted to You under this License for that Work shall terminate
|
|
92
|
-
as of the date such litigation is filed.
|
|
93
|
-
|
|
94
|
-
4. Redistribution. You may reproduce and distribute copies of the
|
|
95
|
-
Work or Derivative Works thereof in any medium, with or without
|
|
96
|
-
modifications, and in Source or Object form, provided that You
|
|
97
|
-
meet the following conditions:
|
|
98
|
-
|
|
99
|
-
(a) You must give any other recipients of the Work or
|
|
100
|
-
Derivative Works a copy of this License; and
|
|
101
|
-
|
|
102
|
-
(b) You must cause any modified files to carry prominent notices
|
|
103
|
-
stating that You changed the files; and
|
|
104
|
-
|
|
105
|
-
(c) You must retain, in the Source form of any Derivative Works
|
|
106
|
-
that You distribute, all copyright, patent, trademark, and
|
|
107
|
-
attribution notices from the Source form of the Work,
|
|
108
|
-
excluding those notices that do not pertain to any part of
|
|
109
|
-
the Derivative Works; and
|
|
110
|
-
|
|
111
|
-
(d) If the Work includes a "NOTICE" text file as part of its
|
|
112
|
-
distribution, then any Derivative Works that You distribute must
|
|
113
|
-
include a readable copy of the attribution notices contained
|
|
114
|
-
within such NOTICE file, excluding those notices that do not
|
|
115
|
-
pertain to any part of the Derivative Works, in at least one
|
|
116
|
-
of the following places: within a NOTICE text file distributed
|
|
117
|
-
as part of the Derivative Works; within the Source form or
|
|
118
|
-
documentation, if provided along with the Derivative Works; or,
|
|
119
|
-
within a display generated by the Derivative Works, if and
|
|
120
|
-
wherever such third-party notices normally appear. The contents
|
|
121
|
-
of the NOTICE file are for informational purposes only and
|
|
122
|
-
do not modify the License. You may add Your own attribution
|
|
123
|
-
notices within Derivative Works that You distribute, alongside
|
|
124
|
-
or as an addendum to the NOTICE text from the Work, provided
|
|
125
|
-
that such additional attribution notices cannot be construed
|
|
126
|
-
as modifying the License.
|
|
127
|
-
|
|
128
|
-
You may add Your own copyright statement to Your modifications and
|
|
129
|
-
may provide additional or different license terms and conditions
|
|
130
|
-
for use, reproduction, or distribution of Your modifications, or
|
|
131
|
-
for any such Derivative Works as a whole, provided Your use,
|
|
132
|
-
reproduction, and distribution of the Work otherwise complies with
|
|
133
|
-
the conditions stated in this License.
|
|
134
|
-
|
|
135
|
-
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
136
|
-
any Contribution intentionally submitted for inclusion in the Work
|
|
137
|
-
by You to the Licensor shall be under the terms and conditions of
|
|
138
|
-
this License, without any additional terms or conditions.
|
|
139
|
-
Notwithstanding the above, nothing herein shall supersede or modify
|
|
140
|
-
the terms of any separate license agreement you may have executed
|
|
141
|
-
with Licensor regarding such Contributions.
|
|
142
|
-
|
|
143
|
-
6. Trademarks. This License does not grant permission to use the trade
|
|
144
|
-
names, trademarks, service marks, or product names of the Licensor,
|
|
145
|
-
except as required for reasonable and customary use in describing the
|
|
146
|
-
origin of the Work and reproducing the content of the NOTICE file.
|
|
147
|
-
|
|
148
|
-
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
149
|
-
agreed to in writing, Licensor provides the Work (and each
|
|
150
|
-
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
151
|
-
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
152
|
-
implied, including, without limitation, any warranties or conditions
|
|
153
|
-
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
154
|
-
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
155
|
-
appropriateness of using or redistributing the Work and assume any
|
|
156
|
-
risks associated with Your exercise of permissions under this License.
|
|
157
|
-
|
|
158
|
-
8. Limitation of Liability. In no event and under no legal theory,
|
|
159
|
-
whether in tort (including negligence), contract, or otherwise,
|
|
160
|
-
unless required by applicable law (such as deliberate and grossly
|
|
161
|
-
negligent acts) or agreed to in writing, shall any Contributor be
|
|
162
|
-
liable to You for damages, including any direct, indirect, special,
|
|
163
|
-
incidental, or consequential damages of any character arising as a
|
|
164
|
-
result of this License or out of the use or inability to use the
|
|
165
|
-
Work (including but not limited to damages for loss of goodwill,
|
|
166
|
-
work stoppage, computer failure or malfunction, or any and all
|
|
167
|
-
other commercial damages or losses), even if such Contributor
|
|
168
|
-
has been advised of the possibility of such damages.
|
|
169
|
-
|
|
170
|
-
9. Accepting Warranty or Additional Liability. While redistributing
|
|
171
|
-
the Work or Derivative Works thereof, You may choose to offer,
|
|
172
|
-
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
173
|
-
or other liability obligations and/or rights consistent with this
|
|
174
|
-
License. However, in accepting such obligations, You may act only
|
|
175
|
-
on Your own behalf and on Your sole responsibility, not on behalf
|
|
176
|
-
of any other Contributor, and only if You agree to indemnify,
|
|
177
|
-
defend, and hold each Contributor harmless for any liability
|
|
178
|
-
incurred by, or claims asserted against, such Contributor by reason
|
|
179
|
-
of your accepting any such warranty or additional liability.
|
|
180
|
-
|
|
181
|
-
END OF TERMS AND CONDITIONS
|
|
182
|
-
|
|
183
|
-
APPENDIX: How to apply the Apache License to your work.
|
|
184
|
-
|
|
185
|
-
To apply the Apache License to your work, attach the following
|
|
186
|
-
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
187
|
-
replaced with your own identifying information. (Don't include
|
|
188
|
-
the brackets!) The text should be enclosed in the appropriate
|
|
189
|
-
comment syntax for the file format. We also recommend that a
|
|
190
|
-
file or class name and description of purpose be included on the
|
|
191
|
-
same "printed page" as the copyright notice for easier
|
|
192
|
-
identification within third-party archives.
|
|
193
|
-
|
|
194
|
-
Copyright [yyyy] [name of copyright owner]
|
|
195
|
-
|
|
196
|
-
Licensed under the Apache License, Version 2.0 (the "License");
|
|
197
|
-
you may not use this file except in compliance with the License.
|
|
198
|
-
You may obtain a copy of the License at
|
|
199
|
-
|
|
200
|
-
http://www.apache.org/licenses/LICENSE-2.0
|
|
201
|
-
|
|
202
|
-
Unless required by applicable law or agreed to in writing, software
|
|
203
|
-
distributed under the License is distributed on an "AS IS" BASIS,
|
|
204
|
-
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
205
|
-
See the License for the specific language governing permissions and
|
|
206
|
-
limitations under the License.
|
|
207
|
-
|
|
5
|
+
Author: Red Hat
|
|
6
|
+
License-Expression: Apache-2.0
|
|
208
7
|
Project-URL: homepage, https://github.com/neuralmagic/guidellm
|
|
8
|
+
Project-URL: source, https://github.com/neuralmagic/guidellm
|
|
9
|
+
Project-URL: issues, https://github.com/neuralmagic/guidellm/issues
|
|
10
|
+
Project-URL: docs, https://github.com/neuralmagic/guidellm/tree/main/docs
|
|
11
|
+
Keywords: ai,benchmarking,deep-learning,deployment,evaluation,guidance,inference,language-models,large-language-model,llm,machine-learning,model-benchmark,model-evaluation,nlp,performance,vllm
|
|
209
12
|
Requires-Python: <4.0,>=3.9.0
|
|
210
13
|
Description-Content-Type: text/markdown
|
|
211
14
|
License-File: LICENSE
|
|
@@ -220,10 +23,12 @@ Requires-Dist: protobuf
|
|
|
220
23
|
Requires-Dist: pydantic>=2.0.0
|
|
221
24
|
Requires-Dist: pydantic-settings>=2.0.0
|
|
222
25
|
Requires-Dist: pyyaml>=6.0.0
|
|
223
|
-
Requires-Dist: requests
|
|
224
26
|
Requires-Dist: rich
|
|
225
27
|
Requires-Dist: transformers
|
|
226
28
|
Provides-Extra: dev
|
|
29
|
+
Requires-Dist: build>=1.0.0; extra == "dev"
|
|
30
|
+
Requires-Dist: setuptools>=61.0; extra == "dev"
|
|
31
|
+
Requires-Dist: setuptools-git-versioning<3,>=2.0; extra == "dev"
|
|
227
32
|
Requires-Dist: pre-commit~=3.5.0; extra == "dev"
|
|
228
33
|
Requires-Dist: scipy~=1.10; extra == "dev"
|
|
229
34
|
Requires-Dist: sphinx~=7.1.2; extra == "dev"
|
|
@@ -234,7 +39,6 @@ Requires-Dist: pytest-asyncio~=0.23.8; extra == "dev"
|
|
|
234
39
|
Requires-Dist: pytest-cov~=5.0.0; extra == "dev"
|
|
235
40
|
Requires-Dist: pytest-mock~=3.14.0; extra == "dev"
|
|
236
41
|
Requires-Dist: pytest-rerunfailures~=14.0; extra == "dev"
|
|
237
|
-
Requires-Dist: requests-mock~=1.12.1; extra == "dev"
|
|
238
42
|
Requires-Dist: respx~=0.22.0; extra == "dev"
|
|
239
43
|
Requires-Dist: mypy~=1.10.1; extra == "dev"
|
|
240
44
|
Requires-Dist: ruff~=0.5.2; extra == "dev"
|
|
@@ -259,7 +63,7 @@ Dynamic: license-file
|
|
|
259
63
|
Scale Efficiently: Evaluate and Optimize Your LLM Deployments for Real-World Inference
|
|
260
64
|
</h3>
|
|
261
65
|
|
|
262
|
-
[](https://github.com/neuralmagic/guidellm/releases) [](https://github.com/neuralmagic/guidellm/tree/main/docs) [](https://github.com/neuralmagic/guidellm/blob/main/LICENSE) [](https://pypi.python.org/pypi/guidellm) [](https://github.com/neuralmagic/guidellm/releases) [](https://github.com/neuralmagic/guidellm/tree/main/docs) [](https://github.com/neuralmagic/guidellm/blob/main/LICENSE) [](https://pypi.python.org/pypi/guidellm) [](https://pypi.python.org/pypi/guidellm) [](https://github.com/neuralmagic/guidellm/actions/workflows/nightly.yml)
|
|
263
67
|
|
|
264
68
|
## Overview
|
|
265
69
|
|
|
@@ -9,7 +9,7 @@
|
|
|
9
9
|
Scale Efficiently: Evaluate and Optimize Your LLM Deployments for Real-World Inference
|
|
10
10
|
</h3>
|
|
11
11
|
|
|
12
|
-
[](https://github.com/neuralmagic/guidellm/releases) [](https://github.com/neuralmagic/guidellm/tree/main/docs) [](https://github.com/neuralmagic/guidellm/blob/main/LICENSE) [](https://pypi.python.org/pypi/guidellm) [](https://github.com/neuralmagic/guidellm/releases) [](https://github.com/neuralmagic/guidellm/tree/main/docs) [](https://github.com/neuralmagic/guidellm/blob/main/LICENSE) [](https://pypi.python.org/pypi/guidellm) [](https://pypi.python.org/pypi/guidellm) [](https://github.com/neuralmagic/guidellm/actions/workflows/nightly.yml)
|
|
13
13
|
|
|
14
14
|
## Overview
|
|
15
15
|
|
|
@@ -0,0 +1,238 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["setuptools >= 61.0", "setuptools-git-versioning>=2.0,<3"]
|
|
3
|
+
build-backend = "setuptools.build_meta"
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
[tool.setuptools.packages.find]
|
|
7
|
+
where = ["src"]
|
|
8
|
+
include = ["*"]
|
|
9
|
+
|
|
10
|
+
[tool.setuptools.package-data]
|
|
11
|
+
"guidellm.data" = ["*.gz"]
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
# ************************************************
|
|
15
|
+
# ********** Project Metadata **********
|
|
16
|
+
# ************************************************
|
|
17
|
+
|
|
18
|
+
[project]
|
|
19
|
+
dynamic = ["version"]
|
|
20
|
+
name = "guidellm"
|
|
21
|
+
description = "Guidance platform for deploying and managing large language models."
|
|
22
|
+
readme = { file = "README.md", content-type = "text/markdown" }
|
|
23
|
+
requires-python = ">=3.9.0,<4.0"
|
|
24
|
+
license = "Apache-2.0"
|
|
25
|
+
license-files = ["LICENSE"]
|
|
26
|
+
authors = [ { name = "Red Hat" } ]
|
|
27
|
+
keywords = [
|
|
28
|
+
"ai",
|
|
29
|
+
"benchmarking",
|
|
30
|
+
"deep-learning",
|
|
31
|
+
"deployment",
|
|
32
|
+
"evaluation",
|
|
33
|
+
"guidance",
|
|
34
|
+
"inference",
|
|
35
|
+
"language-models",
|
|
36
|
+
"large-language-model",
|
|
37
|
+
"llm",
|
|
38
|
+
"machine-learning",
|
|
39
|
+
"model-benchmark",
|
|
40
|
+
"model-evaluation",
|
|
41
|
+
"nlp",
|
|
42
|
+
"performance",
|
|
43
|
+
"vllm",
|
|
44
|
+
]
|
|
45
|
+
dependencies = [
|
|
46
|
+
"click",
|
|
47
|
+
"datasets",
|
|
48
|
+
"ftfy>=6.0.0",
|
|
49
|
+
"httpx[http2]<1.0.0",
|
|
50
|
+
"loguru",
|
|
51
|
+
"numpy",
|
|
52
|
+
"pillow",
|
|
53
|
+
"protobuf",
|
|
54
|
+
"pydantic>=2.0.0",
|
|
55
|
+
"pydantic-settings>=2.0.0",
|
|
56
|
+
"pyyaml>=6.0.0",
|
|
57
|
+
"rich",
|
|
58
|
+
"transformers",
|
|
59
|
+
]
|
|
60
|
+
|
|
61
|
+
[project.optional-dependencies]
|
|
62
|
+
dev = [
|
|
63
|
+
# build
|
|
64
|
+
"build>=1.0.0",
|
|
65
|
+
"setuptools>=61.0",
|
|
66
|
+
"setuptools-git-versioning>=2.0,<3",
|
|
67
|
+
|
|
68
|
+
# general and configurations
|
|
69
|
+
"pre-commit~=3.5.0",
|
|
70
|
+
"scipy~=1.10",
|
|
71
|
+
"sphinx~=7.1.2",
|
|
72
|
+
"tox~=4.16.0",
|
|
73
|
+
|
|
74
|
+
# testing
|
|
75
|
+
"lorem~=0.1.1",
|
|
76
|
+
"pytest~=8.2.2",
|
|
77
|
+
"pytest-asyncio~=0.23.8",
|
|
78
|
+
"pytest-cov~=5.0.0",
|
|
79
|
+
"pytest-mock~=3.14.0",
|
|
80
|
+
"pytest-rerunfailures~=14.0",
|
|
81
|
+
"respx~=0.22.0",
|
|
82
|
+
|
|
83
|
+
# code quality
|
|
84
|
+
"mypy~=1.10.1",
|
|
85
|
+
"ruff~=0.5.2",
|
|
86
|
+
|
|
87
|
+
# docs quality
|
|
88
|
+
"mdformat~=0.7.17",
|
|
89
|
+
"mdformat-footnote~=0.1.1",
|
|
90
|
+
"mdformat-frontmatter~=2.0.8",
|
|
91
|
+
"mdformat-gfm~=0.3.6",
|
|
92
|
+
|
|
93
|
+
# type-checking
|
|
94
|
+
"types-click~=7.1.8",
|
|
95
|
+
"types-PyYAML~=6.0.1",
|
|
96
|
+
"types-requests~=2.32.0",
|
|
97
|
+
"types-toml",
|
|
98
|
+
]
|
|
99
|
+
|
|
100
|
+
[project.urls]
|
|
101
|
+
homepage = "https://github.com/neuralmagic/guidellm"
|
|
102
|
+
source = "https://github.com/neuralmagic/guidellm"
|
|
103
|
+
issues = "https://github.com/neuralmagic/guidellm/issues"
|
|
104
|
+
docs = "https://github.com/neuralmagic/guidellm/tree/main/docs"
|
|
105
|
+
|
|
106
|
+
|
|
107
|
+
[project.entry-points.console_scripts]
|
|
108
|
+
guidellm = "guidellm.__main__:cli"
|
|
109
|
+
|
|
110
|
+
|
|
111
|
+
# ************************************************
|
|
112
|
+
# ********** Code Quality Tools **********
|
|
113
|
+
# ************************************************
|
|
114
|
+
|
|
115
|
+
|
|
116
|
+
[tool.isort]
|
|
117
|
+
profile = "black"
|
|
118
|
+
|
|
119
|
+
|
|
120
|
+
[tool.mypy]
|
|
121
|
+
files = ["src/guidellm", "tests"]
|
|
122
|
+
python_version = '3.9'
|
|
123
|
+
warn_redundant_casts = true
|
|
124
|
+
warn_unused_ignores = false
|
|
125
|
+
show_error_codes = true
|
|
126
|
+
namespace_packages = true
|
|
127
|
+
exclude = ["venv", ".tox"]
|
|
128
|
+
|
|
129
|
+
# Silence "type import errors" as our 3rd-party libs does not have types
|
|
130
|
+
# Check: https://mypy.readthedocs.io/en/latest/config_file.html#import-discovery
|
|
131
|
+
follow_imports = 'silent'
|
|
132
|
+
|
|
133
|
+
[[tool.mypy.overrides]]
|
|
134
|
+
module = ["datasets.*", "tranformers.*", "setuptools.*", "setuptools_git_versioning.*"]
|
|
135
|
+
ignore_missing_imports=true
|
|
136
|
+
|
|
137
|
+
|
|
138
|
+
[tool.ruff]
|
|
139
|
+
line-length = 88
|
|
140
|
+
indent-width = 4
|
|
141
|
+
exclude = ["build", "dist", "env", ".venv"]
|
|
142
|
+
|
|
143
|
+
[tool.ruff.format]
|
|
144
|
+
quote-style = "double"
|
|
145
|
+
indent-style = "space"
|
|
146
|
+
|
|
147
|
+
[tool.ruff.lint]
|
|
148
|
+
ignore = [
|
|
149
|
+
"PLR0913",
|
|
150
|
+
"TCH001",
|
|
151
|
+
"COM812",
|
|
152
|
+
"ISC001",
|
|
153
|
+
"TCH002",
|
|
154
|
+
"PLW1514", # allow Path.open without encoding
|
|
155
|
+
"RET505", # allow `else` blocks
|
|
156
|
+
"RET506", # allow `else` blocks
|
|
157
|
+
"PD011", # ignore .values usage since ruff assumes it's a Pandas DataFrame
|
|
158
|
+
]
|
|
159
|
+
select = [
|
|
160
|
+
# Rules reference: https://docs.astral.sh/ruff/rules/
|
|
161
|
+
|
|
162
|
+
# Code Style / Formatting
|
|
163
|
+
"E", # pycodestyle: checks adherence to PEP 8 conventions including spacing, indentation, and line length
|
|
164
|
+
"W", # pycodestyle: checks adherence to PEP 8 conventions including spacing, indentation, and line length
|
|
165
|
+
"A", # flake8-builtins: prevents shadowing of Python built-in names
|
|
166
|
+
"C", # Convention: ensures code adheres to specific style and formatting conventions
|
|
167
|
+
"COM", # flake8-commas: enforces the correct use of trailing commas
|
|
168
|
+
"ERA", # eradicate: detects commented-out code that should be removed
|
|
169
|
+
"I", # isort: ensures imports are sorted in a consistent manner
|
|
170
|
+
"ICN", # flake8-import-conventions: enforces import conventions for better readability
|
|
171
|
+
"N", # pep8-naming: enforces PEP 8 naming conventions for classes, functions, and variables
|
|
172
|
+
"NPY", # NumPy: enforces best practices for using the NumPy library
|
|
173
|
+
"PD", # pandas-vet: enforces best practices for using the pandas library
|
|
174
|
+
"PT", # flake8-pytest-style: enforces best practices and style conventions for pytest tests
|
|
175
|
+
"PTH", # flake8-use-pathlib: encourages the use of pathlib over os.path for file system operations
|
|
176
|
+
"Q", # flake8-quotes: enforces consistent use of single or double quotes
|
|
177
|
+
"TCH", # flake8-type-checking: enforces type checking practices and standards
|
|
178
|
+
"TID", # flake8-tidy-imports: enforces tidy and well-organized imports
|
|
179
|
+
"RUF022", # flake8-ruff: enforce sorting of __all__ in modules
|
|
180
|
+
|
|
181
|
+
# Code Structure / Complexity
|
|
182
|
+
"C4", # flake8-comprehensions: improves readability and performance of list, set, and dict comprehensions
|
|
183
|
+
"C90", # mccabe: checks for overly complex code using cyclomatic complexity
|
|
184
|
+
"ISC", # flake8-implicit-str-concat: prevents implicit string concatenation
|
|
185
|
+
"PIE", # flake8-pie: identifies and corrects common code inefficiencies and mistakes
|
|
186
|
+
"R", # Refactor: suggests improvements to code structure and readability
|
|
187
|
+
"SIM", # flake8-simplify: simplifies complex expressions and improves code readability
|
|
188
|
+
|
|
189
|
+
# Code Security / Bug Prevention
|
|
190
|
+
"ARG", # flake8-unused-arguments: detects unused function and method arguments
|
|
191
|
+
"ASYNC", # flake8-async: identifies incorrect or inefficient usage patterns in asynchronous code
|
|
192
|
+
"B", # flake8-bugbear: detects common programming mistakes and potential bugs
|
|
193
|
+
"BLE", # flake8-blind-except: prevents blind exceptions that catch all exceptions without handling
|
|
194
|
+
"E", # Error: detects and reports errors in the code
|
|
195
|
+
"F", # Pyflakes: detects unused imports, shadowed imports, undefined variables, and various formatting errors in string operations
|
|
196
|
+
"INP", # flake8-no-pep420: prevents implicit namespace packages by requiring __init__.py
|
|
197
|
+
"PGH", # pygrep-hooks: detects deprecated and dangerous code patterns
|
|
198
|
+
"PL", # Pylint: comprehensive source code analyzer for enforcing coding standards and detecting errors
|
|
199
|
+
"RSE", # flake8-raise: ensures exceptions are raised correctly
|
|
200
|
+
"S", # flake8-bandit: detects security issues and vulnerabilities in the code
|
|
201
|
+
"SLF", # flake8-self: prevents incorrect usage of the self argument in class methods
|
|
202
|
+
"T10", # flake8-debugger: detects the presence of debugging tools such as pdb
|
|
203
|
+
"T20", # flake8-print: detects print statements left in the code
|
|
204
|
+
"UP", # pyupgrade: automatically upgrades syntax for newer versions of Python
|
|
205
|
+
"W", # Warning: provides warnings about potential issues in the code
|
|
206
|
+
"YTT", # flake8-2020: identifies code that will break with future Python releases
|
|
207
|
+
|
|
208
|
+
# Code Documentation
|
|
209
|
+
"FIX", # flake8-fixme: detects FIXMEs and other temporary comments that should be resolved
|
|
210
|
+
]
|
|
211
|
+
|
|
212
|
+
[tool.ruff.lint.extend-per-file-ignores]
|
|
213
|
+
"tests/**/*.py" = [
|
|
214
|
+
"S101", # asserts allowed in tests
|
|
215
|
+
"ARG", # Unused function args allowed in tests
|
|
216
|
+
"PLR2004", # Magic value used in comparison
|
|
217
|
+
"TCH002", # No import only type checking in tests
|
|
218
|
+
"SLF001", # enable private member access in tests
|
|
219
|
+
"S105", # allow hardcoded passwords in tests
|
|
220
|
+
"S311", # allow standard pseudo-random generators in tests
|
|
221
|
+
"PT011", # allow generic exceptions in tests
|
|
222
|
+
"N806", # allow uppercase variable names in tests
|
|
223
|
+
"PGH003", # allow general ignores in tests
|
|
224
|
+
"S106", # allow hardcoded passwords in tests
|
|
225
|
+
"PLR0915", # allow complext statements in tests
|
|
226
|
+
]
|
|
227
|
+
|
|
228
|
+
[tool.ruff.lint.isort]
|
|
229
|
+
known-first-party = ["guidellm", "tests"]
|
|
230
|
+
|
|
231
|
+
|
|
232
|
+
[tool.pytest.ini_options]
|
|
233
|
+
addopts = '-s -vvv --cache-clear'
|
|
234
|
+
markers = [
|
|
235
|
+
"smoke: quick tests to check basic functionality",
|
|
236
|
+
"sanity: detailed tests to ensure major functions work correctly",
|
|
237
|
+
"regression: tests to ensure that new changes do not break existing functionality"
|
|
238
|
+
]
|
|
@@ -0,0 +1,126 @@
|
|
|
1
|
+
import os
|
|
2
|
+
import re
|
|
3
|
+
from pathlib import Path
|
|
4
|
+
from typing import Optional, Union
|
|
5
|
+
|
|
6
|
+
from packaging.version import Version
|
|
7
|
+
from setuptools import setup
|
|
8
|
+
from setuptools_git_versioning import count_since, get_branch, get_sha, get_tags
|
|
9
|
+
|
|
10
|
+
LAST_RELEASE_VERSION = Version("0.0.0")
|
|
11
|
+
TAG_VERSION_PATTERN = re.compile(r"^v(\d+\.\d+\.\d+)$")
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
def get_last_version_diff() -> tuple[Version, Optional[str], Optional[int]]:
|
|
15
|
+
"""
|
|
16
|
+
Get the last version, last tag, and the number of commits since the last tag.
|
|
17
|
+
If no tags are found, return the last release version and None for the tag/commits.
|
|
18
|
+
|
|
19
|
+
:returns: A tuple containing the last version, last tag, and number of commits since
|
|
20
|
+
the last tag.
|
|
21
|
+
"""
|
|
22
|
+
tagged_versions = [
|
|
23
|
+
(Version(match.group(1)), tag)
|
|
24
|
+
for tag in get_tags(root=Path(__file__).parent)
|
|
25
|
+
if (match := TAG_VERSION_PATTERN.match(tag))
|
|
26
|
+
]
|
|
27
|
+
tagged_versions.sort(key=lambda tv: tv[0])
|
|
28
|
+
last_version, last_tag = (
|
|
29
|
+
tagged_versions[-1] if tagged_versions else (LAST_RELEASE_VERSION, None)
|
|
30
|
+
)
|
|
31
|
+
commits_since_last = (
|
|
32
|
+
count_since(last_tag + "^{commit}", root=Path(__file__).parent)
|
|
33
|
+
if last_tag
|
|
34
|
+
else None
|
|
35
|
+
)
|
|
36
|
+
|
|
37
|
+
return last_version, last_tag, commits_since_last
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
def get_next_version(
|
|
41
|
+
build_type: str, build_iteration: Optional[Union[str, int]]
|
|
42
|
+
) -> tuple[Version, Optional[str], int]:
|
|
43
|
+
"""
|
|
44
|
+
Get the next version based on the build type and iteration.
|
|
45
|
+
- build_type == release: take the last version and add a post if build iteration
|
|
46
|
+
- build_type == candidate: increment to next minor, add 'rc' with build iteration
|
|
47
|
+
- build_type == nightly: increment to next minor, add 'a' with build iteration
|
|
48
|
+
- build_type == alpha: increment to next minor, add 'a' with build iteration
|
|
49
|
+
- build_type == dev: increment to next minor, add 'dev' with build iteration
|
|
50
|
+
|
|
51
|
+
:param build_type: The type of build (release, candidate, nightly, alpha, dev).
|
|
52
|
+
:param build_iteration: The build iteration number. If None, defaults to the number
|
|
53
|
+
of commits since the last tag or 0 if no commits since the last tag.
|
|
54
|
+
:returns: A tuple containing the next version, the last tag the version is based
|
|
55
|
+
off of (if any), and the final build iteration used.
|
|
56
|
+
"""
|
|
57
|
+
version, tag, commits_since_last = get_last_version_diff()
|
|
58
|
+
|
|
59
|
+
if not build_iteration and build_iteration != 0:
|
|
60
|
+
build_iteration = commits_since_last or 0
|
|
61
|
+
elif isinstance(build_iteration, str):
|
|
62
|
+
build_iteration = int(build_iteration)
|
|
63
|
+
|
|
64
|
+
if build_type == "release":
|
|
65
|
+
if commits_since_last:
|
|
66
|
+
# add post since we have commits since last tag
|
|
67
|
+
version = Version(f"{version.base_version}.post{build_iteration}")
|
|
68
|
+
return version, tag, build_iteration
|
|
69
|
+
|
|
70
|
+
# not in release pathway, so need to increment to target next release version
|
|
71
|
+
version = Version(f"{version.major}.{version.minor + 1}.0")
|
|
72
|
+
|
|
73
|
+
if build_type == "candidate":
|
|
74
|
+
# add 'rc' since we are in candidate pathway
|
|
75
|
+
version = Version(f"{version}.rc{build_iteration}")
|
|
76
|
+
elif build_type in ["nightly", "alpha"]:
|
|
77
|
+
# add 'a' since we are in nightly or alpha pathway
|
|
78
|
+
version = Version(f"{version}.a{build_iteration}")
|
|
79
|
+
else:
|
|
80
|
+
# assume 'dev' if not in any of the above pathways
|
|
81
|
+
version = Version(f"{version}.dev{build_iteration}")
|
|
82
|
+
|
|
83
|
+
return version, tag, build_iteration
|
|
84
|
+
|
|
85
|
+
|
|
86
|
+
def write_version_files() -> tuple[Path, Path]:
|
|
87
|
+
"""
|
|
88
|
+
Write the version information to version.txt and version.py files.
|
|
89
|
+
version.txt contains the version string.
|
|
90
|
+
version.py contains the version plus additional metadata.
|
|
91
|
+
|
|
92
|
+
:returns: A tuple containing the paths to the version.txt and version.py files.
|
|
93
|
+
"""
|
|
94
|
+
build_type = os.getenv("GUIDELLM_BUILD_TYPE", "dev").lower()
|
|
95
|
+
version, tag, build_iteration = get_next_version(
|
|
96
|
+
build_type=build_type,
|
|
97
|
+
build_iteration=os.getenv("GUIDELLM_BUILD_ITERATION"),
|
|
98
|
+
)
|
|
99
|
+
module_path = Path(__file__).parent / "src" / "guidellm"
|
|
100
|
+
version_txt_path = module_path / "version.txt"
|
|
101
|
+
version_py_path = module_path / "version.py"
|
|
102
|
+
|
|
103
|
+
with version_txt_path.open("w") as file:
|
|
104
|
+
file.write(str(version))
|
|
105
|
+
|
|
106
|
+
with version_py_path.open("w") as file:
|
|
107
|
+
file.writelines(
|
|
108
|
+
[
|
|
109
|
+
f'version = "{version}"\n',
|
|
110
|
+
f'build_type = "{build_type}"\n',
|
|
111
|
+
f'build_iteration = "{build_iteration}"\n',
|
|
112
|
+
f'git_commit = "{get_sha()}"\n',
|
|
113
|
+
f'git_branch = "{get_branch()}"\n',
|
|
114
|
+
f'git_last_tag = "{tag}"\n',
|
|
115
|
+
]
|
|
116
|
+
)
|
|
117
|
+
|
|
118
|
+
return version_txt_path, version_py_path
|
|
119
|
+
|
|
120
|
+
|
|
121
|
+
setup(
|
|
122
|
+
setuptools_git_versioning={
|
|
123
|
+
"enabled": True,
|
|
124
|
+
"version_file": str(write_version_files()[0]),
|
|
125
|
+
}
|
|
126
|
+
)
|
|
@@ -145,7 +145,7 @@ class OpenAIHTTPBackend(Backend):
|
|
|
145
145
|
elif self.model not in models:
|
|
146
146
|
raise ValueError(
|
|
147
147
|
f"Model {self.model} not found in available models:"
|
|
148
|
-
"{models} for target: {self.target}"
|
|
148
|
+
f"{models} for target: {self.target}"
|
|
149
149
|
)
|
|
150
150
|
|
|
151
151
|
async def prepare_multiprocessing(self):
|
|
@@ -202,6 +202,13 @@ class OpenAIHTTPBackend(Backend):
|
|
|
202
202
|
and a ResponseSummary for the final response.
|
|
203
203
|
"""
|
|
204
204
|
logger.debug("{} invocation with args: {}", self.__class__.__name__, locals())
|
|
205
|
+
|
|
206
|
+
if isinstance(prompt, list):
|
|
207
|
+
raise ValueError(
|
|
208
|
+
"List prompts (batching) is currently not supported for "
|
|
209
|
+
f"text_completions OpenAI pathways. Received: {prompt}"
|
|
210
|
+
)
|
|
211
|
+
|
|
205
212
|
headers = self._headers()
|
|
206
213
|
payload = self._completions_payload(
|
|
207
214
|
orig_kwargs=kwargs,
|
|
@@ -298,19 +298,8 @@ class SweepProfile(AsyncProfile):
|
|
|
298
298
|
|
|
299
299
|
min_rate = self.measured_rates[0]
|
|
300
300
|
max_rate = self.measured_rates[1]
|
|
301
|
-
# Increase max rate by one step to hopefully find a better effective rate
|
|
302
|
-
max_rate += (max_rate - min_rate) / self.sweep_size
|
|
303
301
|
rates = np.linspace(min_rate, max_rate, self.sweep_size - 1)[1:]
|
|
304
302
|
|
|
305
|
-
# Round to the next 0.25
|
|
306
|
-
rates = (np.ceil(rates * 8) + 1 ) // 2 / 4
|
|
307
|
-
# Remove duplicates caused by rounding
|
|
308
|
-
rates = np.unique(rates)
|
|
309
|
-
|
|
310
|
-
# End early if we don't have enough rates
|
|
311
|
-
if self.completed_strategies - 1 > len(rates):
|
|
312
|
-
return None
|
|
313
|
-
|
|
314
303
|
if self.rate_type == "constant":
|
|
315
304
|
return AsyncConstantStrategy(
|
|
316
305
|
rate=rates[self.completed_strategies - 2],
|