Skip to content

[0.13.0][Doc] Supplement PD separation parameters of DeepSeek V3.1#6054

Merged
wangxiyuan merged 1 commit intovllm-project:releases/v0.13.0from
dragondream-chen:v0.13.0/doc
Jan 22, 2026
Merged

[0.13.0][Doc] Supplement PD separation parameters of DeepSeek V3.1#6054
wangxiyuan merged 1 commit intovllm-project:releases/v0.13.0from
dragondream-chen:v0.13.0/doc

Conversation

@dragondream-chen
Copy link
Copy Markdown
Collaborator

What this PR does / why we need it?

Supplement PD separation parameters of DeepSeek V3.1
The recommended parameter configuration for DeepSeek V3.1 in the EP32 scenario after PD separation has been adjusted, and the core parameters have been described in detail.

Does this PR introduce any user-facing change?

How was this patch tested?

Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request updates the documentation for DeepSeek V3.1, providing new recommended parameters for a Prefill-Decode (PD) separation deployment. The changes include adjusting speculative decoding settings, GPU memory utilization, and compilation configurations, as well as introducing the VLLM_ASCEND_ENABLE_FLASHCOMM1 environment variable for communication optimization. A new 'Notice' section has been added to explain the core parameters, which greatly improves the clarity of the documentation. The changes are consistent across the different node configurations and appear to be well-considered. I have no concerns with this update.

@weiguihua2 weiguihua2 added ready read for review ready-for-test start test by label for PR labels Jan 20, 2026
Signed-off-by: chenmenglong <chenmenglong1@huawei.com>
@wangxiyuan wangxiyuan merged commit dd997a8 into vllm-project:releases/v0.13.0 Jan 22, 2026
10 checks passed
845473182 pushed a commit to 845473182/vllm-ascend that referenced this pull request Jan 22, 2026
…lm-ascend into FIA_v0.13.0

* 'releases/v0.13.0' of https://github.com/vllm-project/vllm-ascend:
  [0.13.0][Doc] Supplement PD separation parameters of DeepSeek V3.1 (vllm-project#6054)
  [EPLB][Bugfix][v0.13.0] Incorporate the warm up of the EPLB into the profile run. (vllm-project#6099)
  [EPLB][Bugfix] Dispatch Allgather use log2phy if enable eplb (vllm-project#5933) (vllm-project#6016)
  [0.13.0][CI]fix for CI lint (vllm-project#6093)
  [0.13.0][cherry-pick][bugfix] fix the complex and potentially problematic generate_kv_idx. (vllm-project#5955)
starmountain1997 pushed a commit to starmountain1997/vllm-ascend that referenced this pull request Jan 31, 2026
…llm-project#6054)

### What this PR does / why we need it?
Supplement PD separation parameters of DeepSeek V3.1
The recommended parameter configuration for DeepSeek V3.1 in the EP32
scenario after PD separation has been adjusted, and the core parameters
have been described in detail.

Signed-off-by: chenmenglong <chenmenglong1@huawei.com>
tangtiangu pushed a commit to tangtiangu/jiusi-vllm-ascend that referenced this pull request Feb 24, 2026
…llm-project#6054)

### What this PR does / why we need it?
Supplement PD separation parameters of DeepSeek V3.1
The recommended parameter configuration for DeepSeek V3.1 in the EP32
scenario after PD separation has been adjusted, and the core parameters
have been described in detail.

Signed-off-by: chenmenglong <chenmenglong1@huawei.com>
tangtiangu pushed a commit to tangtiangu/jiusi-vllm-ascend that referenced this pull request Feb 24, 2026
…llm-project#6054)

### What this PR does / why we need it?
Supplement PD separation parameters of DeepSeek V3.1
The recommended parameter configuration for DeepSeek V3.1 in the EP32
scenario after PD separation has been adjusted, and the core parameters
have been described in detail.

Signed-off-by: chenmenglong <chenmenglong1@huawei.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ready read for review ready-for-test start test by label for PR

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants