Tencent / Tencent/hpc-ops

Any plan to support DeepSeek V3.2 ?

Open
#33 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
1.2k
Forks
142
Avg merge
23h 15m
Merged PRs (30d)
8

Description

Now the hpc-ops only support num_dim_qk == 128, which limits compatibility with models like DeepSeek V3/V3.2.
Are there any plan to support more head dimensions ?

image image
image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the hpc-ops implementation and checks that restrict num_dim_qk to 128, then trace how supported head dimensions are selected for inference operators. Review any nearby validation or compatibility tests. Done means DeepSeek V3/V3.2 or other non-128 head dimensions are supported without breaking existing cases.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
ai-infra-agents, hpc
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.