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>
Signed-off-by: simon-mo <simon.mo@hey.com>
This commit is contained in:
Yongye Zhu
2025-09-30 05:14:41 -04:00
committed by simon-mo
parent 03df0fb5d2
commit b3230e1ac0
71 changed files with 3915 additions and 218 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
tests/kernels/attention/test_flashmla.py
View File

@@ -97,18 +97,16 @@ def test_flash_mla(b, s_q, mean_sk, h_q, h_kv, d, dv, block_size, causal,
descale_k = None
def flash_mla():
return flash_mla_with_kvcache(
q,
blocked_k,
block_table,
cache_seqlens,
dv,
tile_scheduler_metadata,
num_splits,
causal=causal,
descale_q=descale_q,
descale_k=descale_k,
)
return flash_mla_with_kvcache(q,
blocked_k,
block_table,
cache_seqlens,
dv,
tile_scheduler_metadata,
num_splits,
causal=causal,
descale_q=descale_q,
descale_k=descale_k)
def scaled_dot_product_attention(query, key, value, is_causal=False):
query = query.float()