[Model] Support DeepSeek-V4.1-Flash (#56214)

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: andyluo7 <andy.luo@amd.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Yongye Zhu
2026-09-11 02:11:19 -07:00
committed by GitHub
co-authored by Jee Jee Li andyluo7 OpenAI Codex zjy0516 Claude Opus 5
parent e6821ceac9
commit e77daef89e
49 changed files with 3996 additions and 138 deletions
+2 -2
View File
@@ -58,7 +58,7 @@ from vllm.utils.multi_stream_utils import (
)
from vllm.v1.attention.backend import AttentionBackend, AttentionMetadata
from vllm.v1.attention.backends.mla.indexer import (
DeepseekV4IndexerBackend,
DeepseekV41IndexerBackend,
dsa_indexer_uses_fp4,
get_max_prefill_buffer_size,
)
@@ -1005,7 +1005,7 @@ class DeepseekV4IndexerCache(torch.nn.Module, AttentionLayerBase):
def forward(self): ...
def get_attn_backend(self) -> type[AttentionBackend]:
return DeepseekV4IndexerBackend
return DeepseekV41IndexerBackend
class DeepseekV4Indexer(nn.Module):