Add `lm-eval` directly to requirements-test.txt (#9161)

.buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh

@@ -2,7 +2,7 @@
 # We can use this script to compute baseline accuracy on GSM for transformers.
 #
 # Make sure you have lm-eval-harness installed:
-#   pip install git+https://github.com/EleutherAI/lm-evaluation-harness.git@9516087b81a61d0e220b22cc1b75be76de23bc10
+#   pip install lm-eval==0.4.4
 
 usage() {
     echo``

.buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh

@@ -3,7 +3,7 @@
 # We use this for fp8, which HF does not support.
 #
 # Make sure you have lm-eval-harness installed:
-#   pip install lm-eval==0.4.3
+#   pip install lm-eval==0.4.4
 
 usage() {
     echo``

.buildkite/test-pipeline.yaml

@@ -98,7 +98,6 @@ steps:
   - vllm/
   commands:
   - pip install -e ./plugins/vllm_add_dummy_model
-  - pip install git+https://github.com/EleutherAI/lm-evaluation-harness.git@a4987bba6e9e9b3f22bd3a6c1ecf0abd04fd5622#egg=lm_eval[api]
   - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_lazy_outlines.py --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_generate_multiple_loras.py --ignore=entrypoints/llm/test_guided_generate.py
   - pytest -v -s entrypoints/llm/test_lazy_outlines.py # it needs a clean process
   - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
@@ -278,7 +277,6 @@ steps:
   - csrc/
   - vllm/model_executor/layers/quantization
   commands:
-  - pip install lm-eval
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - bash ./run-tests.sh -c configs/models-small.txt -t 1
 
@@ -492,6 +490,5 @@ steps:
   - csrc/
   - vllm/model_executor/layers/quantization
   commands:
-  - pip install lm-eval
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - bash ./run-tests.sh -c configs/models-large.txt -t 4

docs/source/quantization/fp8.rst

@@ -106,7 +106,7 @@ Install ``vllm`` and ``lm-evaluation-harness``:
 
 .. code-block:: console
 
-   $ pip install vllm lm_eval==0.4.3
+   $ pip install vllm lm-eval==0.4.4
 
 Load and run the model in ``vllm``:
 

requirements-test.txt

@@ -22,6 +22,7 @@ timm # required for internvl test
 transformers_stream_generator # required for qwen-vl test
 matplotlib # required for qwen-vl test
 datamodel_code_generator # required for minicpm3 test
+lm-eval[api]==0.4.4 # required for model evaluation test
 
 # TODO: Add this after fully implementing llava(mantis)
 # git+https://github.com/TIGER-AI-Lab/Mantis.git # required for llava(mantis) test