Conversation
CLA Signature Passlicy666, thanks for your pull request. All authors of the commits have signed the CLA. 👍 |
Contributor
|
📖 文档预览：https://ascend.github.io/docs/pr-preview/pr-157/sources/llm_d/ 也可打开整站首页。 构建自 |
licy666
force-pushed
the
feat/llm-d-quick-start
branch
from
September 21, 2026 02:25
0a06fc4 to
3272513
Compare
CLA Signature Passlicy666, thanks for your pull request. All authors of the commits have signed the CLA. 👍 |
在单卡昇腾上用 vLLM / EPP / Envoy 三个进程跑通 llm-d 无集群最小路径，权重从 Hugging Face 拉取 Qwen3-0.6B，并接入共享 Quick Start 看护。
licy666
force-pushed
the
feat/llm-d-quick-start
branch
from
September 21, 2026 03:17
3272513 to
13d9062
Compare
CLA Signature Passlicy666, thanks for your pull request. All authors of the commits have signed the CLA. 👍 |
Contributor
可以像peft的文档一样，可以不做对比，给一个示例
|
Contributor
这两个代码块要有输出，可以让用户对比
|
Contributor
代码块要有输出，可以让用户对比
|
Contributor
|
Contributor
这个步骤可以删掉
|
This branch has not been deployed
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
sources/llm_d/：单卡、无 Kubernetes，三个普通进程（vLLM worker、EPP、Envoy）跑通最小推理路径。模型是 Hugging Face 的Qwen/Qwen3-0.6B，安装仍是vllm/vllm-ascend0.23.0，最后强制重装triton-ascend==3.2.2。llm_d-quick-start.yml+tests/llm_d子类；首页推理区增加卡片和 toctree。Go / EPP / Envoy 的缓存落在/root/.cache/huggingface/llm_d/，不额外挂 volume。POST :8081/v1/completions返回text_completion/Qwen/Qwen3-0.6B，启动日志有backend=hccl。