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

[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896)

Browse Source 
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:
Yongye Zhu
2025-09-30 05:14:41 -04:00
committed by GitHub
parent e23cacda35
commit fa7e254a7f
71 changed files with 3915 additions and 218 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/attention/selector.py
View File

@@ -144,6 +144,7 @@ def get_attn_backend(
block_size: int,
use_mla: bool = False,
has_sink: bool = False,
use_sparse: bool = False,
) -> type[AttentionBackend]:
"""Selects which attention backend to use and lazily imports it."""
# Accessing envs.* behind an @lru_cache decorator can cause the wrong
@@ -158,6 +159,7 @@ def get_attn_backend(
use_v1=envs.VLLM_USE_V1,
use_mla=use_mla,
has_sink=has_sink,
use_sparse=use_sparse,
)
@@ -170,6 +172,7 @@ def _cached_get_attn_backend(
use_v1: bool = False,
use_mla: bool = False,
has_sink: bool = False,
use_sparse: bool = False,
) -> type[AttentionBackend]:
# Check whether a particular choice of backend was
@@ -203,7 +206,7 @@ def _cached_get_attn_backend(
# get device-specific attn_backend
attention_cls = current_platform.get_attn_backend_cls(
selected_backend, head_size, dtype, kv_cache_dtype, block_size, use_v1,
use_mla, has_sink)
use_mla, has_sink, use_sparse)
if not attention_cls:
raise ValueError(
f"Invalid attention backend for {current_platform.device_name}")