[Doc] sync customization/trace/pd-disagg docs (port slime #1942) - #131
Closed
aoshen02 wants to merge 1 commit into
Closed
[Doc] sync customization/trace/pd-disagg docs (port slime #1942)#131aoshen02 wants to merge 1 commit into
aoshen02 wants to merge 1 commit into
Conversation
Port of THUDM/slime#1942 (update docs). Brought the technical doc updates (customization.md agentic-workflows section, trace.md, pd-disaggregation.md, en+zh), rebranded slime->vime / sglang_rollout->vllm_rollout / SGLang->vLLM. Divergence handling: - README.md / README_zh.md: kept vime's version (slime's changes were SGLang-branded architecture text + 'Projects built upon slime' marketing + an agentic-examples list — vime uses vLLM and trimmed examples in #126). - Dropped the broken examples/search-r1 link from the added customization text (trimmed in vime); kept examples/multi_agent + examples/fully_async (exist). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: aoshen02 <aoshen@inferact.ai>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request rebrands the project from "slime" to "vime" across multiple documentation files, updating import paths and references. It also adds new sections detailing agentic workflows through customization interfaces and expands the explanation of Prefill and Decode (PD) disaggregation. A review comment correctly identifies a typo ("recommand" instead of "recommend") in the English PD disaggregation documentation.
| You can set the number of servers used for Prefill by setting the `--prefill-num-servers` argument. | ||
|
|
||
| We recommand using PD Disaggregation for multi-turn/agentic RL training. | ||
| We recommand using PD Disaggregation for multi-turn/agentic RL training, where rollouts tend to produce long contexts and decode-heavy workloads that benefit from separating prefill and decode resources. |
Contributor
There was a problem hiding this comment.
There is a typo in this line: "recommand" should be "recommend".
Suggested change
| We recommand using PD Disaggregation for multi-turn/agentic RL training, where rollouts tend to produce long contexts and decode-heavy workloads that benefit from separating prefill and decode resources. | |
| We recommend using PD Disaggregation for multi-turn/agentic RL training, where rollouts tend to produce long contexts and decode-heavy workloads that benefit from separating prefill and decode resources. |
Collaborator
Author
|
Closing for now (slime→vime sync being restructured). Branch is preserved — can reopen anytime. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Ports THUDM/slime#1942 (update docs) — technical doc updates only.
sglang_rollout→vllm_rollout, SGLang→vLLM.examples/search-r1link from the added text (trimmed in vime); kept multi_agent + fully_async.Docs-only; ruff/CI n/a to content. Part of #107 sync. 🤖 Generated with Claude Code