[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896)
Signed-off-by: Chen Zhang <zhangch99@outlook.com> Signed-off-by: youkaichao <youkaichao@gmail.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Signed-off-by: mgoin <mgoin64@gmail.com> Signed-off-by: NickLucche <nlucches@redhat.com> Signed-off-by: Yongye Zhu <zyy1102000@gmail.com> Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com> Signed-off-by: Lucia Fang <fanglu@meta.com> Co-authored-by: Chen Zhang <zhangch99@outlook.com> Co-authored-by: youkaichao <youkaichao@gmail.com> Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com> Co-authored-by: yewentao256 <zhyanwentao@126.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com> Co-authored-by: mgoin <mgoin64@gmail.com> Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com> Co-authored-by: Lucia Fang <fanglu@meta.com> Co-authored-by: NickLucche <nlucches@redhat.com> Co-authored-by: Siyuan Fu <siyuanf@nvidia.com> Co-authored-by: Matthew Bonanni <mbonanni@redhat.com> Co-authored-by: Xiaozhu Meng <mxz297@gmail.com> Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
This commit is contained in:
co-authored by
Chen Zhang
youkaichao
Lucas Wilkinson
Robert Shaw
Lucas Wilkinson
yewentao256
Wentao Ye
mgoin
Lucia Fang
Lucia Fang
NickLucche
Siyuan Fu
Matthew Bonanni
Xiaozhu Meng
Barry Kang
parent
e23cacda35
commit
fa7e254a7f
@@ -8,7 +8,8 @@ import pytest
|
||||
|
||||
from vllm import LLM
|
||||
from vllm.utils import GiB_bytes
|
||||
from vllm.v1.core.kv_cache_utils import get_kv_cache_configs
|
||||
from vllm.v1.core.kv_cache_utils import (generate_scheduler_kv_cache_config,
|
||||
get_kv_cache_configs)
|
||||
from vllm.v1.engine.core import EngineCore as V1EngineCore
|
||||
|
||||
from ..utils import create_new_process_for_each_test
|
||||
@@ -62,11 +63,13 @@ def can_initialize(model_arch: str, monkeypatch: pytest.MonkeyPatch,
|
||||
# Avoid calling model.forward()
|
||||
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_configs(
|
||||
kv_cache_configs = get_kv_cache_configs(
|
||||
vllm_config,
|
||||
kv_cache_specs,
|
||||
[10 * GiB_bytes],
|
||||
)[0]
|
||||
)
|
||||
scheduler_kv_cache_config = generate_scheduler_kv_cache_config(
|
||||
kv_cache_configs)
|
||||
|
||||
# gpu_blocks (> 0), cpu_blocks, scheduler_kv_cache_config
|
||||
return 1, 0, scheduler_kv_cache_config
|
||||
|
||||
Reference in New Issue
Block a user