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

Upstream Llama4 Support to Main (#16113)

Browse Source 
Signed-off-by: Aston Zhang <22279212+astonzhang@users.noreply.github.com>
Signed-off-by: Chris Thi <chris.c.thi@gmail.com>
Signed-off-by: drisspg <drisspguessous@gmail.com>
Signed-off-by: Jon Swenson <jmswen@gmail.com>
Signed-off-by: Keyun Tong <tongkeyun@gmail.com>
Signed-off-by: Lu Fang <fanglu@meta.com>
Signed-off-by: Xiaodong Wang <xdwang@meta.com>
Signed-off-by: Yang Chen <yangche@fb.com>
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Signed-off-by: Lu Fang <lufang@fb.com>
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Lucia Fang <fanglu@fb.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Lu Fang
2025-04-07 08:06:27 -07:00
committed by GitHub
parent 8017c8db7f
commit 55dcce91df
43 changed files with 2436 additions and 155 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
tests/models/decoder_only/audio_language/test_ultravox.py
View File

@@ -12,6 +12,7 @@ from vllm.sequence import SampleLogprobs
from ....conftest import HfRunner, VllmRunner
from ....utils import RemoteOpenAIServer
from ...registry import HF_EXAMPLE_MODELS
from ...utils import check_logprobs_close
MODEL_NAME = "fixie-ai/ultravox-v0_5-llama-3_2-1b"
@@ -55,7 +56,10 @@ def server(request, audio_assets):
for key, value in request.param.items()
]
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
with RemoteOpenAIServer(MODEL_NAME,
args,
env_dict={"VLLM_AUDIO_FETCH_TIMEOUT":
"30"}) as remote_server:
yield remote_server
@@ -106,6 +110,10 @@ def run_test(
**kwargs,
):
"""Inference result should be the same between hf and vllm."""
model_info = HF_EXAMPLE_MODELS.find_hf_info(model)
model_info.check_available_online(on_fail="skip")
model_info.check_transformers_version(on_fail="skip")
# NOTE: take care of the order. run vLLM first, and then run HF.
# vLLM needs a fresh new process without cuda initialization.
# if we run HF first, the cuda initialization will be done and it
@@ -156,6 +164,10 @@ def run_multi_audio_test(
num_logprobs: int,
**kwargs,
):
model_info = HF_EXAMPLE_MODELS.find_hf_info(model)
model_info.check_available_online(on_fail="skip")
model_info.check_transformers_version(on_fail="skip")
with vllm_runner(model,
dtype=dtype,
enforce_eager=True,