iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI] Shard LoRA TP distributed tests (#52350)

Browse Source 
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
This commit is contained in:
Kevin H. Luu
2026-09-02 01:16:44 -07:00
committed by GitHub
parent b2558f8da3
commit f5711fa138
1 changed files with 24 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test_areas/lora.yaml
+24 -18
View File
@@ -27,11 +27,12 @@ steps:
- image-build-amd
- label: ":nvidia: (L4) LoRA TP (Distributed)"
- label: ":nvidia: (L4) LoRA TP (Distributed) %N"
key: lora-tp-distributed
timeout_in_minutes: 60
timeout_in_minutes: 25
device: l4
num_devices: 4
parallelism: 4
source_file_dependencies:
- vllm/lora
- vllm/model_executor/layers/fused_moe/
@@ -44,20 +45,22 @@ steps:
- export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
# There is some Tensor Parallelism related processing logic in LoRA that
# requires multi-GPU testing for validation.
- pytest -v -s -x lora/test_chatglm3_tp.py
- pytest -v -s -x lora/test_llama_tp.py
- pytest -v -s -x lora/test_qwen3_with_multi_loras.py
- pytest -v -s -x lora/test_olmoe_tp.py
- pytest -v -s -x lora/test_gptoss_tp.py
- pytest -v -s -x lora/test_qwen35_densemodel_lora.py
- pytest -v -s -x lora/test_gemma4_tp.py
# Timing-balanced static split from per-file walls in builds 83921/83936.
- case "$$BUILDKITE_PARALLEL_JOB" in 0|1|2|3) ;; *) echo "unexpected BUILDKITE_PARALLEL_JOB=$$BUILDKITE_PARALLEL_JOB" && exit 1;; esac
- test "$$BUILDKITE_PARALLEL_JOB" != "3" || pytest -v -s -x lora/test_chatglm3_tp.py
- test "$$BUILDKITE_PARALLEL_JOB" != "1" || pytest -v -s -x lora/test_llama_tp.py
- test "$$BUILDKITE_PARALLEL_JOB" != "3" || pytest -v -s -x lora/test_qwen3_with_multi_loras.py
- test "$$BUILDKITE_PARALLEL_JOB" != "2" || pytest -v -s -x lora/test_olmoe_tp.py
- test "$$BUILDKITE_PARALLEL_JOB" != "0" || pytest -v -s -x lora/test_gptoss_tp.py
- test "$$BUILDKITE_PARALLEL_JOB" != "1" || pytest -v -s -x lora/test_qwen35_densemodel_lora.py
- test "$$BUILDKITE_PARALLEL_JOB" != "2" || pytest -v -s -x lora/test_gemma4_tp.py
mirror:
amd:
label: ":amd: (MI300) LoRA TP (Distributed)"
label: ":amd: (MI300) LoRA TP (Distributed) %N"
dind: false
device: mi300_4
working_dir: "/vllm-workspace/tests"
timeout_in_minutes: 55
timeout_in_minutes: 25
depends_on:
- image-build-amd
source_file_dependencies:
@@ -66,10 +69,13 @@ steps:
- vllm/platforms/rocm.py
- tests/lora
commands:
- pytest -v -s -x lora/test_chatglm3_tp.py
- pytest -v -s -x lora/test_llama_tp.py
- pytest -v -s -x lora/test_qwen3_with_multi_loras.py
- pytest -v -s -x lora/test_olmoe_tp.py
- pytest -v -s -x lora/test_gptoss_tp.py
- pytest -v -s -x lora/test_qwen35_densemodel_lora.py
- pytest -v -s -x lora/test_gemma4_tp.py
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
- case "$$BUILDKITE_PARALLEL_JOB" in 0|1|2|3) ;; *) echo "unexpected BUILDKITE_PARALLEL_JOB=$$BUILDKITE_PARALLEL_JOB" && exit 1;; esac
- test "$$BUILDKITE_PARALLEL_JOB" != "3" || pytest -v -s -x lora/test_chatglm3_tp.py
- test "$$BUILDKITE_PARALLEL_JOB" != "1" || pytest -v -s -x lora/test_llama_tp.py
- test "$$BUILDKITE_PARALLEL_JOB" != "3" || pytest -v -s -x lora/test_qwen3_with_multi_loras.py
- test "$$BUILDKITE_PARALLEL_JOB" != "2" || pytest -v -s -x lora/test_olmoe_tp.py
- test "$$BUILDKITE_PARALLEL_JOB" != "0" || pytest -v -s -x lora/test_gptoss_tp.py
- test "$$BUILDKITE_PARALLEL_JOB" != "1" || pytest -v -s -x lora/test_qwen35_densemodel_lora.py
- test "$$BUILDKITE_PARALLEL_JOB" != "2" || pytest -v -s -x lora/test_gemma4_tp.py