mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-30 21:16:32 +08:00
[Build] Add initial conditional testing spec (#6841)
This commit is contained in:
Simon Mo
GitHub
parent
360bd67cf0
commit
e3c664bfcb
@ -5,11 +5,47 @@
|
||||
# https://github.com/vllm-project/buildkite-ci/blob/main/scripts/test-template-aws.j2
|
||||
# to generate the final pipeline yaml file.
|
||||
|
||||
# Documentation
|
||||
# label(str): the name of the test. emoji allowed.
|
||||
# fast_check(bool): whether to run this on each commit on fastcheck pipeline.
|
||||
# fast_check_only(bool): run this test on fastcheck pipeline only
|
||||
# command(str): the single command to run for tests. incompatible with commands.
|
||||
# commands(list): the list of commands to run for test. incompatbile with command.
|
||||
# mirror_hardwares(list): the list of hardwares to run the test on as well. currently only supports [amd]
|
||||
# gpu(str): override the GPU selection for the test. default is on L4 GPUs. currently only supports a100
|
||||
# num_gpus(int): override the number of GPUs for the test. default to 1 GPU. currently support 2,4.
|
||||
# num_nodes(int): whether to simulate multi-node setup by launch multiple containers on one host,
|
||||
# in this case, commands must be specified. the first command runs on first host, the second
|
||||
# command runs on the second host.
|
||||
# working_dir(str): specify the place where command should execute, default to /vllm-workspace/tests
|
||||
# source_file_dependencies(list): the list of prefix to opt-in the test for, if empty, the test will always run.
|
||||
|
||||
# When adding a test
|
||||
# - If the test belong to an existing group, add it there
|
||||
# - If the test is short, add to any existing step
|
||||
# - If the test takes more than 10min, then it is okay to create a new step.
|
||||
# Note that all steps execute in parallel.
|
||||
|
||||
steps:
|
||||
- label: Async Engine, Inputs, Utils, Worker Test
|
||||
##### fast check tests #####
|
||||
|
||||
- label: Documentation Build # 2min
|
||||
working_dir: "/vllm-workspace/test_docs/docs"
|
||||
fast_check: true
|
||||
fast_check_only: true
|
||||
no_gpu: True
|
||||
commands:
|
||||
- pip install -r requirements-docs.txt
|
||||
- SPHINXOPTS=\"-W\" make html
|
||||
|
||||
- label: Async Engine, Inputs, Utils, Worker Test # 15min
|
||||
fast_check: true
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/async_engine
|
||||
- tests/test_inputs
|
||||
- tests/multimodal
|
||||
- tests/test_utils
|
||||
- tests/worker
|
||||
commands:
|
||||
- pytest -v -s async_engine # Async Engine
|
||||
- pytest -v -s test_inputs.py
|
||||
@ -17,31 +53,12 @@ steps:
|
||||
- pytest -v -s test_utils.py # Utils
|
||||
- pytest -v -s worker # Worker
|
||||
|
||||
- label: Metrics, Tracing Test
|
||||
fast_check: true
|
||||
fast_check_only: true
|
||||
commands:
|
||||
- pytest -v -s metrics # Metrics
|
||||
- "pip install \
|
||||
opentelemetry-sdk \
|
||||
opentelemetry-api \
|
||||
opentelemetry-exporter-otlp \
|
||||
opentelemetry-semantic-conventions-ai" # Tracing
|
||||
- pytest -v -s tracing
|
||||
|
||||
- label: Regression Test
|
||||
mirror_hardwares: [amd]
|
||||
fast_check: true
|
||||
command: pytest -v -s test_regression.py
|
||||
working_dir: "/vllm-workspace/tests" # optional
|
||||
|
||||
- label: AsyncEngine Test
|
||||
#mirror_hardwares: [amd]
|
||||
command: pytest -v -s async_engine
|
||||
|
||||
- label: Basic Correctness Test
|
||||
- label: Basic Correctness Test # 30min
|
||||
mirror_hardwares: [amd]
|
||||
fast_check: true
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/basic_correctness
|
||||
commands:
|
||||
# This flashinfer installation will fail on AMD ROCm, so it is set as optional.
|
||||
- pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.2/flashinfer-0.1.2+cu121torch2.4-cp310-cp310-linux_x86_64.whl || true
|
||||
@ -50,25 +67,211 @@ steps:
|
||||
- VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_chunked_prefill.py
|
||||
- VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_chunked_prefill.py
|
||||
- VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py
|
||||
|
||||
- label: Core Test
|
||||
|
||||
- label: Core Test # 10min
|
||||
mirror_hardwares: [amd]
|
||||
fast_check: true
|
||||
source_file_dependencies:
|
||||
- vllm/core
|
||||
- vllm/distributed
|
||||
- tests/core
|
||||
commands:
|
||||
- pytest -v -s core
|
||||
|
||||
- label: Distributed Comm Ops Test
|
||||
#mirror_hardwares: [amd]
|
||||
- label: Entrypoints Test # 20min
|
||||
fast_check: true
|
||||
mirror_hardwares: [amd]
|
||||
source_file_dependencies:
|
||||
- vllm/entrypoints
|
||||
- tests/entrypoints
|
||||
commands:
|
||||
- pytest -v -s entrypoints/llm
|
||||
- pytest -v -s entrypoints/openai
|
||||
|
||||
- label: Distributed Tests (4 GPUs) # 10min
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
num_gpus: 4
|
||||
fast_check: true
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/distributed
|
||||
- tests/spec_decode/e2e/test_integration_dist_tp4
|
||||
commands:
|
||||
- pytest -v -s distributed/test_pynccl.py
|
||||
- pytest -v -s spec_decode/e2e/test_integration_dist_tp4.py
|
||||
|
||||
##### fast check tests #####
|
||||
##### 1 GPU test #####
|
||||
|
||||
- label: Metrics, Tracing Test # 10min
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/metrics
|
||||
- tests/tracing
|
||||
commands:
|
||||
- pytest -v -s metrics
|
||||
- "pip install \
|
||||
opentelemetry-sdk \
|
||||
opentelemetry-api \
|
||||
opentelemetry-exporter-otlp \
|
||||
opentelemetry-semantic-conventions-ai"
|
||||
- pytest -v -s tracing
|
||||
|
||||
- label: Regression Test # 5min
|
||||
mirror_hardwares: [amd]
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/test_regression
|
||||
command: pytest -v -s test_regression.py
|
||||
working_dir: "/vllm-workspace/tests" # optional
|
||||
|
||||
- label: Engine Test # 10min
|
||||
mirror_hardwares: [amd]
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/engine
|
||||
- tests/tokenization
|
||||
commands:
|
||||
- pytest -v -s engine test_sequence.py test_config.py test_logger.py
|
||||
# OOM in the CI unless we run this separately
|
||||
- pytest -v -s tokenization
|
||||
|
||||
- label: Examples Test # 12min
|
||||
working_dir: "/vllm-workspace/examples"
|
||||
mirror_hardwares: [amd]
|
||||
source_file_dependencies:
|
||||
- vllm/entrypoints
|
||||
- examples/
|
||||
commands:
|
||||
- pip install awscli tensorizer # for llava example and tensorizer test
|
||||
- python3 offline_inference.py
|
||||
- python3 cpu_offload.py
|
||||
- python3 offline_inference_with_prefix.py
|
||||
- python3 llm_engine_example.py
|
||||
- python3 llava_example.py
|
||||
- python3 tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors
|
||||
|
||||
- label: Models Test # 1hr10min
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/models
|
||||
commands:
|
||||
- pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.2/flashinfer-0.1.2+cu121torch2.4-cp310-cp310-linux_x86_64.whl
|
||||
- pytest -v -s models -m \"not vlm\"
|
||||
|
||||
- label: Vision Language Models Test # 42min
|
||||
mirror_hardwares: [amd]
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
commands:
|
||||
- pytest -v -s models -m vlm
|
||||
|
||||
- label: Prefix Caching Test # 7min
|
||||
mirror_hardwares: [amd]
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/prefix_caching
|
||||
commands:
|
||||
- pytest -v -s prefix_caching
|
||||
|
||||
- label: Samplers Test # 18min
|
||||
source_file_dependencies:
|
||||
- vllm/model_executor/layers
|
||||
- vllm/sampling_metadata.py
|
||||
- tests/samplers
|
||||
command: pytest -v -s samplers
|
||||
|
||||
- label: LogitsProcessor Test # 5min
|
||||
mirror_hardwares: [amd]
|
||||
source_file_dependencies:
|
||||
- vllm/model_executor/layers
|
||||
- tests/test_logits_processor
|
||||
command: pytest -v -s test_logits_processor.py
|
||||
|
||||
- label: Speculative decoding tests # 22min
|
||||
source_file_dependencies:
|
||||
- vllm/spec_decode
|
||||
- tests/spec_decode
|
||||
commands:
|
||||
# See https://github.com/vllm-project/vllm/issues/5152
|
||||
- export VLLM_ATTENTION_BACKEND=XFORMERS
|
||||
- pytest -v -s spec_decode
|
||||
|
||||
- label: LoRA Test %N # 30min each
|
||||
source_file_dependencies:
|
||||
- vllm/lora
|
||||
- csrc/punica
|
||||
- tests/lora
|
||||
command: pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_long_context.py
|
||||
parallelism: 4
|
||||
|
||||
- label: Kernels Test %N # 30min each
|
||||
source_file_dependencies:
|
||||
- csrc/
|
||||
- vllm/attention
|
||||
- tests/kernels
|
||||
commands:
|
||||
- pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.2/flashinfer-0.1.2+cu121torch2.4-cp310-cp310-linux_x86_64.whl
|
||||
- pytest -v -s kernels --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||
parallelism: 4
|
||||
|
||||
- label: Tensorizer Test # 11min
|
||||
soft_fail: true
|
||||
source_file_dependencies:
|
||||
- vllm/model_executor/model_loader
|
||||
- tests/tensorizer_loader
|
||||
commands:
|
||||
- apt-get install -y curl libsodium23
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s tensorizer_loader
|
||||
|
||||
- label: Benchmarks # 9min
|
||||
working_dir: "/vllm-workspace/.buildkite"
|
||||
mirror_hardwares: [amd]
|
||||
source_file_dependencies:
|
||||
- benchmarks/
|
||||
commands:
|
||||
- pip install aiohttp
|
||||
- bash run-benchmarks.sh
|
||||
|
||||
- label: Quantization Test # 15min
|
||||
source_file_dependencies:
|
||||
- csrc/
|
||||
- vllm/model_executor/layers/quantization
|
||||
- tests/quantization
|
||||
command: pytest -v -s quantization
|
||||
|
||||
- label: LM Eval Small Models # 53min
|
||||
working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
|
||||
source_file_dependencies:
|
||||
- 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
|
||||
|
||||
|
||||
##### 1 GPU test #####
|
||||
##### multi gpus test #####
|
||||
|
||||
- label: Distributed Comm Ops Test # 7min
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
num_gpus: 2
|
||||
source_file_dependencies:
|
||||
- vllm/distributed
|
||||
- tests/distributed
|
||||
commands:
|
||||
- pytest -v -s distributed/test_comm_ops.py
|
||||
- pytest -v -s distributed/test_shm_broadcast.py
|
||||
|
||||
- label: 2 Node Tests (4 GPUs in total)
|
||||
- label: 2 Node Tests (4 GPUs in total) # 16min
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
num_gpus: 2
|
||||
num_nodes: 2
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/distributed/test_same_node
|
||||
commands:
|
||||
- # the following commands are for the first node, with ip 192.168.10.10 (ray environment already set up)
|
||||
- VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py
|
||||
@ -76,10 +279,13 @@ steps:
|
||||
- # the following commands are for the second node, with ip 192.168.10.11 (ray environment already set up)
|
||||
- VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py
|
||||
|
||||
- label: Distributed Tests (2 GPUs)
|
||||
- label: Distributed Tests (2 GPUs) # 28min
|
||||
mirror_hardwares: [amd]
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
num_gpus: 2
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/distributed
|
||||
commands:
|
||||
- VLLM_TEST_SAME_HOST=1 torchrun --nproc-per-node=4 distributed/test_same_node.py
|
||||
- TARGET_TEST_SUITE=L4 pytest -v -s distributed/test_basic_distributed_correctness.py
|
||||
@ -89,176 +295,36 @@ steps:
|
||||
- CUDA_VISIBLE_DEVICES=0,1 pytest -v -s test_sharded_state_loader.py
|
||||
- CUDA_VISIBLE_DEVICES=0,1 pytest -v -s distributed/test_utils.py
|
||||
|
||||
- label: Distributed Tests (4 GPUs)
|
||||
#mirror_hardwares: [amd]
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
num_gpus: 4
|
||||
fast_check: true
|
||||
commands:
|
||||
- pytest -v -s distributed/test_pynccl.py
|
||||
- pytest -v -s spec_decode/e2e/test_integration_dist_tp4.py
|
||||
|
||||
- label: Pipeline Parallelism Test
|
||||
- label: Pipeline Parallelism Test # 23min
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
num_gpus: 4
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/distributed/test_pipeline_parallel
|
||||
commands:
|
||||
- pytest -v -s distributed/test_pipeline_parallel.py
|
||||
|
||||
- label: Engine Test
|
||||
mirror_hardwares: [amd]
|
||||
- label: LoRA Long Context (Distributed) # 11min
|
||||
# This test runs llama 13B, so it is required to run on 4 GPUs.
|
||||
num_gpus: 4
|
||||
source_file_dependencies:
|
||||
- vllm/lora
|
||||
- csrc/punica
|
||||
- tests/lora/test_long_context
|
||||
commands:
|
||||
- pytest -v -s engine test_sequence.py test_config.py test_logger.py
|
||||
# OOM in the CI unless we run this separately
|
||||
- pytest -v -s tokenization
|
||||
|
||||
- label: Entrypoints Test
|
||||
fast_check: true
|
||||
mirror_hardwares: [amd]
|
||||
|
||||
commands:
|
||||
- pytest -v -s entrypoints/llm
|
||||
- pytest -v -s entrypoints/openai
|
||||
|
||||
- label: Examples Test
|
||||
working_dir: "/vllm-workspace/examples"
|
||||
mirror_hardwares: [amd]
|
||||
commands:
|
||||
# install tensorizer for tensorize_vllm_model.py
|
||||
- pip install awscli tensorizer
|
||||
- python3 offline_inference.py
|
||||
- python3 cpu_offload.py
|
||||
- python3 offline_inference_with_prefix.py
|
||||
- python3 llm_engine_example.py
|
||||
- python3 offline_inference_vision_language.py
|
||||
- python3 tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors
|
||||
|
||||
- label: Inputs Test
|
||||
#mirror_hardwares: [amd]
|
||||
commands:
|
||||
- pytest -v -s test_inputs.py
|
||||
- pytest -v -s multimodal
|
||||
|
||||
# - label: Kernels Test %N
|
||||
# #mirror_hardwares: [amd]
|
||||
# commands:
|
||||
# - pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.0.8/flashinfer-0.0.8+cu121torch2.3-cp310-cp310-linux_x86_64.whl
|
||||
# - pytest -v -s kernels --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||
# parallelism: 4
|
||||
|
||||
- label: Models Test
|
||||
#mirror_hardwares: [amd]
|
||||
commands:
|
||||
- pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.2/flashinfer-0.1.2+cu121torch2.4-cp310-cp310-linux_x86_64.whl
|
||||
- pytest -v -s models -m \"not vlm\"
|
||||
|
||||
- label: Vision Language Models Test
|
||||
mirror_hardwares: [amd]
|
||||
commands:
|
||||
- pytest -v -s models -m vlm
|
||||
|
||||
- label: Prefix Caching Test
|
||||
mirror_hardwares: [amd]
|
||||
commands:
|
||||
- pytest -v -s prefix_caching
|
||||
|
||||
- label: Samplers Test
|
||||
#mirror_hardwares: [amd]
|
||||
command: pytest -v -s samplers
|
||||
|
||||
- label: LogitsProcessor Test
|
||||
mirror_hardwares: [amd]
|
||||
command: pytest -v -s test_logits_processor.py
|
||||
|
||||
- label: Utils Test
|
||||
commands:
|
||||
- pytest -v -s test_utils.py
|
||||
- pytest -v -s test_embedded_commit.py
|
||||
|
||||
- label: Worker Test
|
||||
mirror_hardwares: [amd]
|
||||
command: pytest -v -s worker
|
||||
|
||||
- label: Speculative decoding tests
|
||||
#mirror_hardwares: [amd]
|
||||
commands:
|
||||
# See https://github.com/vllm-project/vllm/issues/5152
|
||||
- export VLLM_ATTENTION_BACKEND=XFORMERS
|
||||
- pytest -v -s spec_decode
|
||||
|
||||
# - label: LoRA Test %N
|
||||
# #mirror_hardwares: [amd]
|
||||
# command: pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_long_context.py
|
||||
# parallelism: 4
|
||||
|
||||
# - label: LoRA Long Context (Distributed)
|
||||
# #mirror_hardwares: [amd]
|
||||
# num_gpus: 4
|
||||
# # This test runs llama 13B, so it is required to run on 4 GPUs.
|
||||
# commands:
|
||||
# # FIXIT: find out which code initialize cuda before running the test
|
||||
# # before the fix, we need to use spawn to test it
|
||||
# - export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
# - pytest -v -s -x lora/test_long_context.py
|
||||
|
||||
- label: Tensorizer Test
|
||||
#mirror_hardwares: [amd]
|
||||
fast_check: true
|
||||
commands:
|
||||
- apt-get install -y curl libsodium23
|
||||
# FIXIT: find out which code initialize cuda before running the test
|
||||
# before the fix, we need to use spawn to test it
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s tensorizer_loader
|
||||
- pytest -v -s -x lora/test_long_context.py
|
||||
|
||||
- label: Metrics Test
|
||||
mirror_hardwares: [amd]
|
||||
command: pytest -v -s metrics
|
||||
##### multi gpus test #####
|
||||
##### A100 test #####
|
||||
|
||||
- label: Quantization Test
|
||||
#mirror_hardwares: [amd]
|
||||
command: pytest -v -s quantization
|
||||
|
||||
- label: Tracing Test
|
||||
commands:
|
||||
- "pip install \
|
||||
opentelemetry-sdk \
|
||||
opentelemetry-api \
|
||||
opentelemetry-exporter-otlp \
|
||||
opentelemetry-semantic-conventions-ai"
|
||||
- pytest -v -s tracing
|
||||
|
||||
- label: Benchmarks
|
||||
working_dir: "/vllm-workspace/.buildkite"
|
||||
mirror_hardwares: [amd]
|
||||
commands:
|
||||
- pip install aiohttp
|
||||
- bash run-benchmarks.sh
|
||||
|
||||
- label: LM Eval Small Models
|
||||
working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
|
||||
commands:
|
||||
- pip install lm-eval
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- bash ./run-tests.sh -c configs/models-small.txt -t 1
|
||||
|
||||
- label: LM Eval Large Models
|
||||
gpu: a100
|
||||
num_gpus: 4
|
||||
working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
|
||||
commands:
|
||||
- pip install lm-eval
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- bash ./run-tests.sh -c configs/models-large.txt -t 4
|
||||
|
||||
- label: Documentation Build
|
||||
working_dir: "/vllm-workspace/test_docs/docs"
|
||||
fast_check: true
|
||||
no_gpu: True
|
||||
commands:
|
||||
- pip install -r requirements-docs.txt
|
||||
- SPHINXOPTS=\"-W\" make html
|
||||
|
||||
- label: Distributed Tests (A100)
|
||||
- label: Distributed Tests (A100) # optional
|
||||
gpu: a100
|
||||
num_gpus: 4
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
commands:
|
||||
# NOTE: don't test llama model here, it seems hf implementation is buggy
|
||||
# see https://github.com/vllm-project/vllm/pull/5689 for details
|
||||
@ -266,3 +332,15 @@ steps:
|
||||
- pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.2/flashinfer-0.1.2+cu121torch2.4-cp310-cp310-linux_x86_64.whl
|
||||
- TARGET_TEST_SUITE=A100 pytest -v -s distributed/test_basic_distributed_correctness.py
|
||||
- pytest -v -s -x lora/test_mixtral.py
|
||||
|
||||
- label: LM Eval Large Models # optional
|
||||
gpu: a100
|
||||
num_gpus: 4
|
||||
working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
|
||||
source_file_dependencies:
|
||||
- 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
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user