Move authentication guide to README

triton-inference-server · Nov 7, 2024 · b2009cc · b2009cc
1 parent 81a03d9
commit b2009cc
Show file tree

Hide file tree

Showing 4 changed files with 38 additions and 44 deletions.
diff --git a/genai-perf/README.md b/genai-perf/README.md
@@ -309,6 +309,24 @@ inference. Other modes such as the [embeddings](docs/embeddings.md) and
 
 </br>
 
+<!--
+======================
+AUTHENTICATION
+======================
+-->
+
+## Authentication
+
+GenAI-Perf can benchmark secure endpoints such as OpenAI, which requires API
+key authentication. To do so, you must add your API key directly in the command.
+At the end of your command, append the below flags. Replace the key with your
+API key. The `--` flag allows arguments to pass directly into Perf Analyzer in
+superuser mode. The `-H` flag is used to add HTTP headers.
+
+```bash
+-- -H "Authorization: Bearer ${API_KEY}" -H "Accept: text/event-stream"
+```
+
 <!--
 ======================
 METRICS

diff --git a/genai-perf/docs/tutorial.md b/genai-perf/docs/tutorial.md
@@ -163,17 +163,6 @@ Example output:
 └───────────────────────────────────┴──────────┴──────────┴──────────┴──────────┴──────────┴──────────┘
 ```
 
-### Running with Authentication
-GenAI-Perf can benchmark secure endpoints such as OpenAI, which requires API
-key authentication. To do so, you can add your API key directly in the command.
-At the end of your command, append the below flags. Replace the key with your
-API key. The `--` flag allows arguments to pass directly into Perf Analyzer in
-superuser mode. The `-H` flag is used to add HTTP headers.
-
-```bash
--- -H "Authorization: Bearer ${OPENAI_API_KEY}" -H "Accept: text/event-stream"
-```
-
 ## Profile GPT-2 running on OpenAI Completions API-Compatible Server <a id="openai-completions"></a>
 
 Serve the model on the vLLM server with [OpenAI Completions API](https://platform.openai.com/docs/api-reference/completions) endpoint:
@@ -211,14 +200,3 @@ Example output:
 │      Request throughput (per sec) │   2.28 │    N/A │    N/A │    N/A │    N/A │    N/A │
 └───────────────────────────────────┴────────┴────────┴────────┴────────┴────────┴────────┘
 ```
-
-### Running with Authentication
-GenAI-Perf can benchmark secure endpoints such as OpenAI, which requires API
-key authentication. To do so, you can add your API key directly in the command.
-At the end of your command, append the below flags. Replace the key with your
-API key. The `--` flag allows arguments to pass directly into Perf Analyzer in
-superuser mode. The `-H` flag is used to add HTTP headers.
-
-```bash
--- -H "Authorization: Bearer ${OPENAI_API_KEY}" -H "Accept: text/event-stream"
-```
diff --git a/templates/genai-perf-templates/README_template b/templates/genai-perf-templates/README_template
@@ -309,6 +309,26 @@ inference. Other modes such as the [embeddings](docs/embeddings.md) and
 
 </br>
 
+<!--
+======================
+AUTHENTICATION
+======================
+-->
+
+## Authentication
+
+GenAI-Perf can benchmark secure endpoints such as OpenAI, which requires API
+key authentication. To do so, you must add your API key directly in the command.
+At the end of your command, append the below flags. Replace the key with your
+API key. The `--` flag allows arguments to pass directly into Perf Analyzer in
+superuser mode. The `-H` flag is used to add HTTP headers.
+
+```bash
+-- -H "Authorization: Bearer ${API_KEY}" -H "Accept: text/event-stream"
+```
+
+</br>
+
 <!--
 ======================
 METRICS

diff --git a/templates/genai-perf-templates/tutorial_template b/templates/genai-perf-templates/tutorial_template
@@ -163,17 +163,6 @@ Example output:
 └───────────────────────────────────┴──────────┴──────────┴──────────┴──────────┴──────────┴──────────┘
 ```
 
-### Running with Authentication
-GenAI-Perf can benchmark secure endpoints such as OpenAI, which requires API
-key authentication. To do so, you can add your API key directly in the command.
-At the end of your command, append the below flags. Replace the key with your
-API key. The `--` flag allows arguments to pass directly into Perf Analyzer in
-superuser mode. The `-H` flag is used to add HTTP headers.
-
-```bash
--- -H "Authorization: Bearer ${OPENAI_API_KEY}" -H "Accept: text/event-stream"
-```
-
 ## Profile GPT-2 running on OpenAI Completions API-Compatible Server <a id="openai-completions"></a>
 
 Serve the model on the vLLM server with [OpenAI Completions API](https://platform.openai.com/docs/api-reference/completions) endpoint:
@@ -211,14 +200,3 @@ Example output:
 │      Request throughput (per sec) │   2.28 │    N/A │    N/A │    N/A │    N/A │    N/A │
 └───────────────────────────────────┴────────┴────────┴────────┴────────┴────────┴────────┘
 ```
-
-### Running with Authentication
-GenAI-Perf can benchmark secure endpoints such as OpenAI, which requires API
-key authentication. To do so, you can add your API key directly in the command.
-At the end of your command, append the below flags. Replace the key with your
-API key. The `--` flag allows arguments to pass directly into Perf Analyzer in
-superuser mode. The `-H` flag is used to add HTTP headers.
-
-```bash
--- -H "Authorization: Bearer ${OPENAI_API_KEY}" -H "Accept: text/event-stream"
-```