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

17
tests/models/test_initialization.py
View File

@@ -7,6 +7,8 @@ from transformers import PretrainedConfig
from vllm import LLM
from vllm.engine.llm_engine import LLMEngine as V0LLMEngine
from vllm.utils import GiB_bytes
from vllm.v1.core.kv_cache_utils import get_kv_cache_config
from vllm.v1.engine.core import EngineCore as V1EngineCore
from .registry import HF_EXAMPLE_MODELS
@@ -42,14 +44,21 @@ def test_can_initialize(model_arch):
self.cache_config.num_gpu_blocks = 0
self.cache_config.num_cpu_blocks = 0
def _initalize_kv_caches_v1(self, vllm_config):
# gpu_blocks (> 0), cpu_blocks
return 1, 0
def _initialize_kv_caches_v1(self, vllm_config):
kv_cache_specs = self.model_executor.get_kv_cache_specs()
scheduler_kv_cache_config = get_kv_cache_config(
vllm_config,
kv_cache_specs[0],
20 * GiB_bytes,
)
# gpu_blocks (> 0), cpu_blocks, scheduler_kv_cache_config
return 1, 0, scheduler_kv_cache_config
with (patch.object(V0LLMEngine, "_initialize_kv_caches",
_initialize_kv_caches_v0),
patch.object(V1EngineCore, "_initialize_kv_caches",
_initalize_kv_caches_v1)):
_initialize_kv_caches_v1)):
LLM(
model_info.default,
tokenizer=model_info.tokenizer,