Skip to content

MTP support DeepSeekV3.2 #4263

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −0
Open

MTP support DeepSeekV3.2 #4263

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions vllm_ascend/spec_decode/mtp_proposer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,8 @@
_MTP_MODELS = {
"DeepseekV3ForCausalLM":
("vllm.model_executor.models.deepseek_mtp", "DeepSeekMTP"),
"DeepseekV32ForCausalLM":
("vllm.model_executor.models.deepseek_mtp", "DeepSeekMTP"),
Comment on lines +58 to +59
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Nov 19, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

The MTP implementation for DeepseekV32ForCausalLM is identical to that of DeepseekV3ForCausalLM. This creates code duplication. To enhance maintainability and prevent potential bugs should the implementation path change in the future, it would be better to define this shared implementation path as a constant and reuse it for both model architectures.

For example:

DEEPSEEK_MTP_IMPL = ("vllm.model_executor.models.deepseek_mtp", "DeepSeekMTP")

_MTP_MODELS = {
    "DeepseekV3ForCausalLM": DEEPSEEK_MTP_IMPL,
    "DeepseekV32ForCausalLM": DEEPSEEK_MTP_IMPL,
    "Qwen3NextForCausalLM":
    ("vllm_ascend.models.qwen3_next_mtp", "CustomQwen3NextMTP")
}

"Qwen3NextForCausalLM":
("vllm_ascend.models.qwen3_next_mtp", "CustomQwen3NextMTP")
}
Expand Down
Loading