biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Hardware][TPU][V1] Multi-LoRA implementation for the V1 TPU backend (#14238)

Browse Source 
Signed-off-by: Akshat Tripathi <akshat@krai.ai>
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: Chengji Yao <chengjiyao@google.com>
This commit is contained in:
Akshat Tripathi
2025-05-07 21:28:47 +01:00
committed by GitHub
parent db593aa67f
commit c20ef40fd0
19 changed files with 929 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh
View File

@@ -50,6 +50,9 @@ docker run --privileged --net host --shm-size=16G -it \
&& pytest -s -v /workspace/vllm/tests/v1/entrypoints/llm/test_struct_output_generate.py \
&& echo TEST_12 \
&& pytest -s -v /workspace/vllm/tests/tpu/test_moe_pallas.py" \
# Disable the TPU LoRA tests until the feature is activated
# && echo TEST_13 \
# && pytest -s -v /workspace/vllm/tests/tpu/lora/" \
# TODO: This test fails because it uses RANDOM_SEED sampling