20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Consolidate Llama model usage in tests (#13094)

Browse Source
This commit is contained in:
Harry Mellor 2025-02-14 06:18:03 +00:00 committed by GitHub
parent 40932d7a05
commit f2b20fe491
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
22 changed files with 45 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
tests/basic_correctness/test_basic_correctness.py
View File

@ -17,7 +17,7 @@ from ..utils import multi_gpu_test
MODELS = [
"google/gemma-2-2b-it",
"meta-llama/Llama-3.2-1B",
"meta-llama/Llama-3.2-1B-Instruct",
]
TARGET_TEST_SUITE = os.environ.get("TARGET_TEST_SUITE", "L4")
@ -96,12 +96,12 @@ def test_models(
"test_suite", [
("facebook/opt-125m", "ray", "", "L4"),
("facebook/opt-125m", "mp", "", "L4"),
("meta-llama/Llama-2-7b-hf", "ray", "", "L4"),
("meta-llama/Llama-2-7b-hf", "mp", "", "L4"),
("meta-llama/Llama-3.2-1B-Instruct", "ray", "", "L4"),
("meta-llama/Llama-3.2-1B-Instruct", "mp", "", "L4"),
("facebook/opt-125m", "ray", "", "A100"),
("facebook/opt-125m", "mp", "", "A100"),
("facebook/opt-125m", "mp", "FLASHINFER", "A100"),
("meta-llama/Meta-Llama-3-8B", "ray", "FLASHINFER", "A100"),
("meta-llama/Llama-3.2-1B-Instruct", "ray", "FLASHINFER", "A100"),
])
def test_models_distributed(
hf_runner,
@ -116,7 +116,7 @@ def test_models_distributed(
if test_suite != TARGET_TEST_SUITE:
pytest.skip(f"Skip test for {test_suite}")
if model == "meta-llama/Llama-2-7b-hf" and distributed_executor_backend == "ray" and attention_backend == "" and test_suite == "L4": # noqa
if model == "meta-llama/Llama-3.2-1B-Instruct" and distributed_executor_backend == "ray" and attention_backend == "" and test_suite == "L4": # noqa
# test ray adag
os.environ['VLLM_USE_RAY_SPMD_WORKER'] = "1"
os.environ['VLLM_USE_RAY_COMPILED_DAG'] = "1"

6
tests/basic_correctness/test_chunked_prefill.py
View File

@ -20,7 +20,7 @@ from ..utils import multi_gpu_test
MODELS = [
"facebook/opt-125m",
"meta-llama/Llama-3.2-1B",
"meta-llama/Llama-3.2-1B-Instruct",
]
@ -92,7 +92,7 @@ def test_models_distributed(
) -> None:
override_backend_env_variable(monkeypatch, attention_backend)
if (model == "meta-llama/Llama-2-7b-hf"
if (model == "meta-llama/Llama-3.2-1B-Instruct"
and distributed_executor_backend == "ray"):
# test ray adag
os.environ['VLLM_USE_RAY_SPMD_WORKER'] = "1"
@ -221,7 +221,7 @@ def test_with_prefix_caching(
Checks exact match decode with and without prefix caching
with chunked prefill enabled.
"""
model = "meta-llama/Llama-2-7b-chat-hf"
model = "meta-llama/Llama-3.2-1B-Instruct"
# The common prompt has 142 tokens with Llama-2 tokenizer.
common_prompt = "You are a helpful AI assistant " * 20
unique_prompts = [

2
tests/basic_correctness/test_cpu_offload.py
View File

@ -4,5 +4,5 @@ from ..utils import compare_two_settings
def test_cpu_offload():
compare_two_settings("meta-llama/Llama-3.2-1B", [],
compare_two_settings("meta-llama/Llama-3.2-1B-Instruct", [],
["--cpu-offload-gb", "1"])

2
tests/basic_correctness/test_cumem.py
View File

@ -118,7 +118,7 @@ def test_cumem_with_cudagraph():
@pytest.mark.parametrize(
"model",
[
"meta-llama/Llama-3.2-1B", # sleep mode with safetensors
"meta-llama/Llama-3.2-1B-Instruct", # sleep mode with safetensors
"facebook/opt-125m" # sleep mode with pytorch checkpoint
])
def test_end_to_end(model):

2
tests/compile/test_basic_correctness.py
View File

@ -26,7 +26,7 @@ class TestSetting:
test_settings = [
# basic llama model
TestSetting(
model="meta-llama/Llama-3.2-1B",
model="meta-llama/Llama-3.2-1B-Instruct",
model_args=[],
pp_size=2,
tp_size=2,

16
tests/compile/utils.py
View File

@ -6,7 +6,6 @@ import torch
from tests.quantization.utils import is_quant_method_supported
from vllm import LLM, SamplingParams
from vllm.config import CompilationLevel
from vllm.platforms import current_platform
TEST_MODELS = [
@ -15,14 +14,14 @@ TEST_MODELS = [
"dtype": torch.float16,
"quantization": "compressed-tensors"
}),
("neuralmagic/Meta-Llama-3-8B-Instruct-FP8", {
("neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic", {
"dtype": torch.float16,
"quantization": "fp8"
}),
("nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token-2048-Samples", {
"quantization": "compressed-tensors"
}),
("meta-llama/Meta-Llama-3-8B", {}),
("neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", {
"quantization": "compressed-tensors"
}),
("meta-llama/Llama-3.2-1B-Instruct", {}),
]
if is_quant_method_supported("aqlm"):
@ -69,11 +68,6 @@ def check_full_graph_support(model,
# make sure these models can be captured in full graph mode
os.environ["VLLM_TEST_DYNAMO_FULLGRAPH_CAPTURE"] = "1"
# The base meta llama uses too much memory.
if (model == "meta-llama/Meta-Llama-3-8B"
and optimization_level >= CompilationLevel.PIECEWISE):
return
print(f"MODEL={model}")
prompts = [

4
tests/distributed/test_pipeline_parallel.py
View File

@ -162,7 +162,7 @@ TEXT_GENERATION_MODELS = {
"internlm/internlm2-chat-7b": PPTestSettings.fast(),
"inceptionai/jais-13b-chat": PPTestSettings.fast(),
"ai21labs/Jamba-tiny-dev": PPTestSettings.fast(),
"meta-llama/Meta-Llama-3-8B": PPTestSettings.detailed(),
"meta-llama/Llama-3.2-1B-Instruct": PPTestSettings.detailed(),
"openbmb/MiniCPM-2B-sft-bf16": PPTestSettings.fast(),
"openbmb/MiniCPM3-4B": PPTestSettings.fast(),
# Uses Llama
@ -230,7 +230,7 @@ MULTIMODAL_MODELS = {
TEST_MODELS = [
# [LANGUAGE GENERATION]
"microsoft/Phi-3.5-MoE-instruct",
"meta-llama/Meta-Llama-3-8B",
"meta-llama/Llama-3.2-1B-Instruct",
"ibm/PowerLM-3b",
# [LANGUAGE EMBEDDING]
"intfloat/e5-mistral-7b-instruct",

2
tests/entrypoints/openai/test_serving_models.py
View File

@ -14,7 +14,7 @@ from vllm.entrypoints.openai.serving_models import (BaseModelPath,
OpenAIServingModels)
from vllm.lora.request import LoRARequest
MODEL_NAME = "meta-llama/Llama-2-7b"
MODEL_NAME = "meta-llama/Llama-3.2-1B-Instruct"
BASE_MODEL_PATHS = [BaseModelPath(name=MODEL_NAME, model_path=MODEL_NAME)]
LORA_LOADING_SUCCESS_MESSAGE = (
"Success: LoRA adapter '{lora_name}' added successfully.")

2
tests/entrypoints/openai/test_shutdown.py
View File

@ -5,7 +5,7 @@ import pytest
from ...utils import RemoteOpenAIServer
MODEL_NAME = "meta-llama/Llama-3.2-1B"
MODEL_NAME = "meta-llama/Llama-3.2-1B-Instruct"
@pytest.mark.asyncio

10
tests/kv_transfer/disagg_test.py
View File

@ -28,7 +28,7 @@ def setup_servers():
"-m",
"vllm.entrypoints.openai.api_server",
"--model",
"meta-llama/Meta-Llama-3.1-8B-Instruct",
"meta-llama/Llama-3.2-1B-Instruct",
"--port",
"8100",
"--gpu-memory-utilization",
@ -49,7 +49,7 @@ def setup_servers():
"-m",
"vllm.entrypoints.openai.api_server",
"--model",
"meta-llama/Meta-Llama-3.1-8B-Instruct",
"meta-llama/Llama-3.2-1B-Instruct",
"--port",
"8200",
"--gpu-memory-utilization",
@ -100,8 +100,7 @@ def test_disaggregated_prefilling(prompt):
response = requests.post("http://localhost:8100/v1/completions",
headers={"Content-Type": "application/json"},
json={
"model":
"meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.2-1B-Instruct",
"prompt": prompt,
"max_tokens": 1,
"temperature": 0
@ -112,8 +111,7 @@ def test_disaggregated_prefilling(prompt):
response = requests.post("http://localhost:8200/v1/completions",
headers={"Content-Type": "application/json"},
json={
"model":
"meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.2-1B-Instruct",
"prompt": prompt,
"max_tokens": 10,
"temperature": 0

8
tests/models/decoder_only/language/test_fp8.py
View File

@ -26,12 +26,12 @@ os.environ["TOKENIZERS_PARALLELISM"] = "true"
# Test FP8 checkpoint w. fp8_e4m3 kv-cache scaling factors.
("fp8_e4m3", "meta-llama/Llama-3.2-1B-Instruct",
"nm-testing/Llama-3.2-1B-Instruct-FP8-KV"),
# Test FP16 checkpoint w. fp8_e5m2 kv-cache.
# Test BF16 checkpoint w. fp8_e5m2 kv-cache.
("fp8_e5m2", "meta-llama/Llama-3.2-1B-Instruct",
"meta-llama/Llama-3.2-1B-Instruct"),
# Test FP16 checkpoint w. fp8_e4m3 kv-cache scaling factors in json.
("fp8_e4m3", "meta-llama/Llama-2-7b-chat-hf",
"meta-llama/Llama-2-7b-chat-hf")
# Test BF16 checkpoint w. fp8_e4m3 kv-cache scaling factors in json.
("fp8_e4m3", "meta-llama/Llama-3.2-1B-Instruct",
"meta-llama/Llama-3.2-1B-Instruct")
])
# Due to low-precision numerical divergence, we only test logprob of 4 tokens
@pytest.mark.parametrize("max_tokens", [4])

2
tests/models/registry.py
View File

@ -141,7 +141,7 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
"JAISLMHeadModel": _HfExamplesInfo("inceptionai/jais-13b-chat"),
"JambaForCausalLM": _HfExamplesInfo("ai21labs/AI21-Jamba-1.5-Mini",
extras={"tiny": "ai21labs/Jamba-tiny-dev"}), # noqa: E501
"LlamaForCausalLM": _HfExamplesInfo("meta-llama/Meta-Llama-3-8B"),
"LlamaForCausalLM": _HfExamplesInfo("meta-llama/Llama-3.2-1B-Instruct"),
"LLaMAForCausalLM": _HfExamplesInfo("decapoda-research/llama-7b-hf",
is_available_online=False),
"MambaForCausalLM": _HfExamplesInfo("state-spaces/mamba-130m-hf"),

2
tests/quantization/test_register_quantization_config.py
View File

@ -99,7 +99,7 @@ def test_register_quantization_config():
@pytest.mark.parametrize(argnames="model",
argvalues=[
"meta-llama/Meta-Llama-3-8B-Instruct",
"meta-llama/Llama-3.2-1B-Instruct",
])
def test_custom_quant(vllm_runner, model):
"""Test infer with the custom quantization method."""

2
tests/samplers/test_ignore_eos.py
View File

@ -10,7 +10,7 @@ from vllm import SamplingParams
# We also test with llama because it has generation_config to specify EOS
# (past regression).
MODELS = ["facebook/opt-125m", "meta-llama/Llama-2-7b-hf"]
MODELS = ["facebook/opt-125m", "meta-llama/Llama-3.2-1B-Instruct"]
@pytest.mark.parametrize("model", MODELS)

6
tests/spec_decode/e2e/test_compatibility.py
View File

@ -8,7 +8,7 @@ from .conftest import get_output_from_llm_generator
@pytest.mark.parametrize("common_llm_kwargs", [{
"model": "meta-llama/Llama-2-7b-chat-hf",
"model": "meta-llama/Llama-3.2-1B-Instruct",
"speculative_model": "JackFram/llama-68m",
"num_speculative_tokens": 5,
}])
@ -27,8 +27,8 @@ from .conftest import get_output_from_llm_generator
},
{
# Speculative max model len > target max model len should raise.
# https://huggingface.co/meta-llama/Llama-2-7b-chat-hf/blob/f5db02db724555f92da89c216ac04704f23d4590/config.json#L12
"speculative_max_model_len": 4096 + 1,
# https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/9213176726f574b556790deb65791e0c5aa438b6/config.json#L18
"speculative_max_model_len": 131072 + 1,
},
])
@pytest.mark.parametrize("test_llm_kwargs", [{}])

2
tests/test_config.py
View File

@ -251,7 +251,7 @@ def test_rope_customization():
@pytest.mark.parametrize(("model_id", "is_encoder_decoder"), [
("facebook/opt-125m", False),
("facebook/bart-base", True),
("meta-llama/Llama-3.2-1B", False),
("meta-llama/Llama-3.2-1B-Instruct", False),
("meta-llama/Llama-3.2-11B-Vision", True),
])
def test_is_encoder_decoder(model_id, is_encoder_decoder):

8
tests/test_sharded_state_loader.py
View File

@ -46,9 +46,9 @@ def test_filter_subtensors():
@pytest.fixture(scope="module")
def llama_2_7b_files():
def llama_3p2_1b_files():
with TemporaryDirectory() as cache_dir:
input_dir = snapshot_download("meta-llama/Llama-3.2-1B",
input_dir = snapshot_download("meta-llama/Llama-3.2-1B-Instruct",
cache_dir=cache_dir,
ignore_patterns=["*.bin*", "original/*"])
@ -81,13 +81,13 @@ def _run_generate(input_dir, queue: mp.Queue, **kwargs):
@pytest.mark.parametrize("enable_lora", [False, True])
@pytest.mark.parametrize("tp_size", [1, 2])
def test_sharded_state_loader(enable_lora, tp_size, num_gpus_available,
llama_2_7b_files):
llama_3p2_1b_files):
if num_gpus_available < tp_size:
pytest.skip(f"Not enough GPUs for tensor parallelism {tp_size}")
weights_patterns = ("*.safetensors", )
gpu_memory_utilization = 0.8
input_dir = llama_2_7b_files
input_dir = llama_3p2_1b_files
ctx = mp.get_context("spawn")
# Run in separate processes for memory & CUDA isolation

2
tests/tokenization/test_detokenize.py
View File

@ -31,7 +31,7 @@ TOKENIZERS = [
"bigscience/bloom-560m",
"mosaicml/mpt-7b",
"tiiuae/falcon-7b",
"meta-llama/Llama-2-7b-hf",
"meta-llama/Llama-3.2-1B-Instruct",
"codellama/CodeLlama-7b-hf",
"mistralai/Pixtral-12B-2409",
]

4
tests/tokenization/test_get_eos.py
View File

@ -9,7 +9,7 @@ from vllm.transformers_utils.tokenizer import get_tokenizer
def test_get_llama3_eos_token():
model_name = "meta-llama/Meta-Llama-3-8B-Instruct"
model_name = "meta-llama/Llama-3.2-1B-Instruct"
tokenizer = get_tokenizer(model_name)
assert tokenizer.eos_token_id == 128009
@ -17,7 +17,7 @@ def test_get_llama3_eos_token():
generation_config = try_get_generation_config(model_name,
trust_remote_code=False)
assert generation_config is not None
assert generation_config.eos_token_id == [128001, 128009]
assert generation_config.eos_token_id == [128001, 128008, 128009]
def test_get_blip2_eos_token():

2
tests/v1/engine/test_async_llm.py
View File

@ -17,7 +17,7 @@ if not current_platform.is_cuda():
pytest.skip(reason="V1 currently only supported on CUDA.",
allow_module_level=True)
ENGINE_ARGS = AsyncEngineArgs(model="meta-llama/Llama-3.2-1B",
ENGINE_ARGS = AsyncEngineArgs(model="meta-llama/Llama-3.2-1B-Instruct",
enforce_eager=True,
disable_log_requests=True)

2
tests/v1/sample/test_logprobs.py
View File

@ -14,7 +14,7 @@ from vllm import SamplingParams
from ...conftest import VllmRunner
MODEL = "meta-llama/Llama-3.2-1B"
MODEL = "meta-llama/Llama-3.2-1B-Instruct"
DTYPE = "half"

2
tests/v1/sample/test_logprobs_e2e.py
View File

@ -11,7 +11,7 @@ RTOL = 0.03
EXPECTED_VALUE = 0.62
# FIXME(rob): enable prefix caching once supported.
MODEL = "meta-llama/Llama-3.2-1B"
MODEL = "meta-llama/Llama-3.2-1B-Instruct"
MODEL_ARGS = f"pretrained={MODEL},enforce_eager=True,enable_prefix_caching=False" # noqa: E501
SERVER_ARGS = [
"--enforce_eager", "--no_enable_prefix_caching", "--disable-log-requests"