A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[TPU][Bugfix] Fixes prompt_token_ids error in tpu tests. (#23574)
Signed-off-by: Pate Motter <patemotter@google.com>
Pate Motter committed
Aug 25, 2025 at 14:29 UTC
c34c82b7fe5f62e771334bdafc0c4559856ce58f
2 files changed
+2
-2
.buildkite/scripts/hardware_ci/run-tpu-v1-test-part2.sh
+1
-1
@@ -61,7 +61,7 @@ echo "Results will be stored in: $RESULTS_DIR"
61
echo "--- Installing Python dependencies ---"
62
python3 -m pip install --progress-bar off git+https://github.com/thuml/depyf.git \
63
&& python3 -m pip install --progress-bar off pytest pytest-asyncio tpu-info \
64
- && python3 -m pip install --progress-bar off lm_eval[api]==0.4.4 \
64
+ && python3 -m pip install --progress-bar off "lm-eval @ git+https://github.com/EleutherAI/lm-evaluation-harness.git@206b7722158f58c35b7ffcd53b035fdbdda5126d" \
65
&& python3 -m pip install --progress-bar off hf-transfer
66
echo "--- Python dependencies installed ---"
67
export VLLM_USE_V1=1
.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh
+1
-1
@@ -61,7 +61,7 @@ echo "Results will be stored in: $RESULTS_DIR"
61
echo "--- Installing Python dependencies ---"
62
python3 -m pip install --progress-bar off git+https://github.com/thuml/depyf.git \
63
&& python3 -m pip install --progress-bar off pytest pytest-asyncio tpu-info \
64
- && python3 -m pip install --progress-bar off lm_eval[api]==0.4.4 \
64
+ && python3 -m pip install --progress-bar off "lm-eval @ git+https://github.com/EleutherAI/lm-evaluation-harness.git@206b7722158f58c35b7ffcd53b035fdbdda5126d" \
65
&& python3 -m pip install --progress-bar off hf-transfer
66
echo "--- Python dependencies installed ---"
67
export VLLM_USE_V1=1