[CI] Install sgl-eval from PyPI through the test extra (#37504)

docs/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2.mdx

@@ -849,7 +849,7 @@ Results on AIME 2025 (8×B200), evaluated with [sgl-eval](https://github.com/sgl
 **Reproduction.** Install [sgl-eval](https://github.com/sgl-project/sgl-eval), launch the server with the tool-call and reasoning parsers, then run `sgl-eval run`. The AIME 2025 dataset ships with sgl-eval, and thinking is on by default for it:
 
 ```bash Command
-pip install git+https://github.com/sgl-project/sgl-eval.git
+pip install sgl-eval
 
 sgl-eval run aime25 \
   --base-url http://localhost:30000/v1 \

docs/cookbook/autoregressive/Google/Gemma4.mdx

@@ -1455,7 +1455,7 @@ Median ITL (ms):                         15.11
 Reproduce against a running server (`--base-url` points at your endpoint):
 
 ```bash Command
-pip install git+https://github.com/sgl-project/sgl-eval
+pip install sgl-eval
 
 # Sanity-check the endpoint
 sgl-eval ping --base-url http://localhost:30000/v1

docs/cookbook/autoregressive/MiniMax/MiniMax-M2.7.mdx

@@ -497,7 +497,7 @@ This section uses **industry-standard configurations** for comparable benchmark
 - Prompt: `eval/aai/mcq-4choices` (4-choice multiple choice, matching [Artificial Analysis methodology](https://artificialanalysis.ai/methodology/intelligence-benchmarking)) -- sgl-eval's default for this benchmark
 - Evaluation command:
 ```bash Command
-pip install git+https://github.com/sgl-project/sgl-eval.git
+pip install sgl-eval
 
 sgl-eval run gpqa \
     --base-url http://localhost:30000/v1 \

docs/cookbook/autoregressive/Moonshotai/Kimi-K2.6.mdx

@@ -628,7 +628,7 @@ python tool_calls_eval.py tool-calls/samples.jsonl \
 **Evaluation Command:**
 
 ```shell Command
-pip install git+https://github.com/sgl-project/sgl-eval.git
+pip install sgl-eval
 
 # The dataset ships with sgl-eval; --n-repeats runs all 32 samples per problem.
 sgl-eval run aime25 \