[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:
co-authored by
Jee Jee Li
andyluo7
OpenAI Codex
zjy0516
Claude Opus 5
parent
e6821ceac9
commit
e77daef89e
@@ -17,9 +17,9 @@ def _resolve_dspark_attention_backend(
|
||||
) -> AttentionBackendEnum | None:
|
||||
if draft_backend is not None:
|
||||
return draft_backend
|
||||
# DeepSeek-V4 draft layers share the target's KV-cache layout. Other
|
||||
# DeepSeek-V4(.1) draft layers share the target's KV-cache layout. Other
|
||||
# DSpark architectures may use a different attention kind.
|
||||
if draft_model_config.hf_config.model_type == "deepseek_v4":
|
||||
if draft_model_config.hf_config.model_type in ("deepseek_v4", "deepseek_v41"):
|
||||
if target_backend is not None:
|
||||
logger.info_once(
|
||||
"Using the target model's %s attention backend for the "
|
||||
|
||||
Reference in New Issue
Block a user