guidellm 0.3.0a26__py3-none-any.whl → 0.3.0a29__py3-none-any.whl
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-0.3.0a26.dist-info → guidellm-0.3.0a29.dist-info}/METADATA +7 -7
- {guidellm-0.3.0a26.dist-info → guidellm-0.3.0a29.dist-info}/RECORD +6 -6
- {guidellm-0.3.0a26.dist-info → guidellm-0.3.0a29.dist-info}/WHEEL +0 -0
- {guidellm-0.3.0a26.dist-info → guidellm-0.3.0a29.dist-info}/entry_points.txt +0 -0
- {guidellm-0.3.0a26.dist-info → guidellm-0.3.0a29.dist-info}/licenses/LICENSE +0 -0
- {guidellm-0.3.0a26.dist-info → guidellm-0.3.0a29.dist-info}/top_level.txt +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: guidellm
|
|
3
|
-
Version: 0.3.
|
|
3
|
+
Version: 0.3.0a29
|
|
4
4
|
Summary: Guidance platform for deploying and managing large language models.
|
|
5
5
|
Author: Red Hat
|
|
6
6
|
License-Expression: Apache-2.0
|
|
@@ -119,7 +119,7 @@ vllm serve "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16"
|
|
|
119
119
|
|
|
120
120
|
For more information on starting a vLLM server, see the [vLLM Documentation](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html).
|
|
121
121
|
|
|
122
|
-
For information on starting other supported inference servers or platforms, see the [Supported Backends
|
|
122
|
+
For information on starting other supported inference servers or platforms, see the [Supported Backends Documentation](https://github.com/neuralmagic/guidellm/blob/main/docs/backends.md).
|
|
123
123
|
|
|
124
124
|
#### 2. Run a GuideLLM Benchmark
|
|
125
125
|
|
|
@@ -147,13 +147,13 @@ After the evaluation is completed, GuideLLM will summarize the results into thre
|
|
|
147
147
|
|
|
148
148
|
The sections will look similar to the following: <img alt="Sample GuideLLM benchmark output" src="https://raw.githubusercontent.com/neuralmagic/guidellm/main/docs/assets/sample-output.png" />
|
|
149
149
|
|
|
150
|
-
For more details about the metrics and definitions, please refer to the [Metrics
|
|
150
|
+
For more details about the metrics and definitions, please refer to the [Metrics Documentation](https://github.com/neuralmagic/guidellm/blob/main/docs/metrics.md).
|
|
151
151
|
|
|
152
152
|
#### 4. Explore the Results File
|
|
153
153
|
|
|
154
154
|
By default, the full results, including complete statistics and request data, are saved to a file `benchmarks.json` in the current working directory. This file can be used for further analysis or reporting, and additionally can be reloaded into Python for further analysis using the `guidellm.benchmark.GenerativeBenchmarksReport` class. You can specify a different file name and extension with the `--output` argument.
|
|
155
155
|
|
|
156
|
-
For more details about the supported output file types, please take a look at the [Outputs
|
|
156
|
+
For more details about the supported output file types, please take a look at the [Outputs Documentation](https://github.com/neuralmagic/guidellm/blob/main/docs/outputs.md).
|
|
157
157
|
|
|
158
158
|
#### 5. Use the Results
|
|
159
159
|
|
|
@@ -161,7 +161,7 @@ The results from GuideLLM are used to optimize your LLM deployment for performan
|
|
|
161
161
|
|
|
162
162
|
For example, when deploying a chat application, we likely want to ensure that our time to first token (TTFT) and inter-token latency (ITL) are under certain thresholds to meet our service level objectives (SLOs) or service level agreements (SLAs). For example, setting TTFT to 200ms and ITL 25ms for the sample data provided in the example above, we can see that even though the server is capable of handling up to 13 requests per second, we would only be able to meet our SLOs for 99% of users at a request rate of 3.5 requests per second. If we relax our constraints on ITL to 50 ms, then we can meet the TTFT SLA for 99% of users at a request rate of approximately 10 requests per second.
|
|
163
163
|
|
|
164
|
-
For further details on determining the optimal request rate and SLOs, refer to the [SLOs
|
|
164
|
+
For further details on determining the optimal request rate and SLOs, refer to the [SLOs Documentation](https://github.com/neuralmagic/guidellm/blob/main/docs/service_level_objectives.md).
|
|
165
165
|
|
|
166
166
|
### Configurations
|
|
167
167
|
|
|
@@ -254,7 +254,7 @@ In the future this will be replaced by a configurable untracked file for dev use
|
|
|
254
254
|
|
|
255
255
|
### Documentation
|
|
256
256
|
|
|
257
|
-
Our comprehensive documentation offers detailed guides and resources to help you maximize the benefits of GuideLLM. Whether just getting started or looking to dive deeper into advanced topics, you can find what you need in our [
|
|
257
|
+
Our comprehensive documentation offers detailed guides and resources to help you maximize the benefits of GuideLLM. Whether just getting started or looking to dive deeper into advanced topics, you can find what you need in our [Documentation](https://github.com/neuralmagic/guidellm/blob/main/docs).
|
|
258
258
|
|
|
259
259
|
### Core Docs
|
|
260
260
|
|
|
@@ -279,7 +279,7 @@ We appreciate contributions to the code, examples, integrations, documentation,
|
|
|
279
279
|
|
|
280
280
|
### Releases
|
|
281
281
|
|
|
282
|
-
Visit our [GitHub Releases
|
|
282
|
+
Visit our [GitHub Releases Page](https://github.com/neuralmagic/guidellm/releases) and review the release notes to stay updated with the latest releases.
|
|
283
283
|
|
|
284
284
|
### License
|
|
285
285
|
|
|
@@ -47,9 +47,9 @@ guidellm/utils/hf_datasets.py,sha256=C99cB4StbhjC8XtnzLLGe6A0TYrs63EapQZJQmQr8dI
|
|
|
47
47
|
guidellm/utils/hf_transformers.py,sha256=3iF40l02VEWOcS8kasO8TSws0Lp3cE-NyiqoB9GnHuA,1021
|
|
48
48
|
guidellm/utils/random.py,sha256=elA8HZ3AIN5T2pa7cgq35OVK__0SQmZVS4IzxJaOpvw,1310
|
|
49
49
|
guidellm/utils/text.py,sha256=Xn6JUWy3B7gi1l0UkBFLizV9fnZ_kM3OQDMLlIZqsgE,6347
|
|
50
|
-
guidellm-0.3.
|
|
51
|
-
guidellm-0.3.
|
|
52
|
-
guidellm-0.3.
|
|
53
|
-
guidellm-0.3.
|
|
54
|
-
guidellm-0.3.
|
|
55
|
-
guidellm-0.3.
|
|
50
|
+
guidellm-0.3.0a29.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
|
|
51
|
+
guidellm-0.3.0a29.dist-info/METADATA,sha256=6QftATtbar6xsLHBGS_TCnSyoRjKGpTyi7Fa87_1_-g,19344
|
|
52
|
+
guidellm-0.3.0a29.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
53
|
+
guidellm-0.3.0a29.dist-info/entry_points.txt,sha256=DzLFEg47fF7qY1b-9laPz9jg0KSKJ1_D9TbF93kLz_E,51
|
|
54
|
+
guidellm-0.3.0a29.dist-info/top_level.txt,sha256=EXRGjnvFtL6MeZTe0tnHRMYcEWUW3vEqoG2zO7vFOtk,9
|
|
55
|
+
guidellm-0.3.0a29.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|