Packaging and versioning for benchmarking tools and utilities / 基准测试工具和实用程序的打包与版本管理
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 25/100
- Issue 类型
- 功能
- 描述清晰度
- 需要澄清
- 活跃度
- 冷清
- 技术栈
- docker, python
- 领域
- build-system, release, tooling
调研方向
The issue names no files, tests, or entry points. Start by reviewing the existing benchmarking utilities and the team's internal Docker packaging approach, then check with maintainers whether Docker, PyPI, or both fit the project's direction. Done means an agreed official versioning and packaging plan is defined.
由索引模型根据 Issue 内容生成。
描述
Is your feature request related to a problem? Please describe.
My team has been using InferenceX in our automated testing workflow to generate workloads and run benchmarks. The benchmarking utilities are proving to be a critical tool for both simulating workloads and tracking performance metrics. Right now, there doesn't seem to be an official versioning or packaging process for those tools, which makes it trickier to integrate into our testing environment. Currently, we're handling this by packaging them into in an internal Docker image and including the latest commit hash inside the image.
Describe the solution you'd like
Even though the main focus of the InferenceX project is to create timely and reliable benchmarks of the current state of the inference software ecosystem, Official, versioned releases of InferenceX tools and scripts could be useful for the broader community. Are there plans to publish official versioned releases either via a Docker image, a PyPI package, or both? We'd be happy to help start this work by adapting our current packaging work and creating a PR, but we first wanted to check with maintainers and the community to make sure that is consistent with the future direction of the project.
Describe alternatives you've considered
- Continuing to refine our internal Docker image that vendors InferenceX.
- Creating and maintaining our own Python package that bundles the InferenceX benchmarking utilities, rather than relying on an official package.
Additional context
Not that I can think of at the moment. We mainly wanted to understand the project's long term goals related to versioning and packaging, and express our willingness to contribute to a broad solution.
中文说明
功能请求：目前 InferenceX 的基准测试工具和脚本缺少官方的版本管理和打包流程，这使得集成到自动化测试环境中变得困难。请求发布官方版本化的工具，可通过 Docker 镜像、PyPI 包或两者发布。提问者愿意贡献代码来推动此工作。备选方案包括继续维护内部 Docker 镜像或自行打包 InferenceX 基准测试工具。
- 主要语言
- Python
- 星标
- 1.9k
- 派生
- 343
- 平均合并
- 2 天 40 分钟
- 30 天内合并 PR
- 431
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
SemiAnalysisAI/InferenceX 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 68/100
SemiAnalysisAI/InferenceX#2125 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 68/100
SemiAnalysisAI/InferenceX#1587 ·
维护者通常 1 天内回复
-
[experimental chore/agentx-v0.2-aiperf-testing branch] agentic build_replay_cmd: missing --tokenizer-trust-remote-code breaks Kimi-K2.5 (and other custom-code tokenizer models) / agentic build_replay_cmd 缺少 --tokenizer-trust-remote-code 导致 Kimi-K2.5 等自定义 tokenizer 模型失败可能重新可做 @sahil-bhatti-ai 于 170 天前认领，目前没有进行中的 PR。 未关闭
难度 1/5 1 小时以内 新手友好度 78/100
SemiAnalysisAI/InferenceX#1369 · 3 条评论 ·
维护者通常 1 天内回复
-
难度 1/5 1-3 小时 新手友好度 76/100
SemiAnalysisAI/InferenceX#1359 · 1 条评论 ·
维护者通常 1 天内回复
-
难度 2/5 1 小时以内 新手友好度 18/100
SemiAnalysisAI/InferenceX#4655 · 1 条评论 ·
维护者通常 1 天内回复
查看 SemiAnalysisAI/InferenceX 的全部 Issue
相似的 Issue
-
bug
难度 2/5 1-3 小时 新手友好度 86/100
NousResearch/hermes-agent#147104 ·
维护者通常 1 天内回复
-
[oblt-aw][autodoc] Document new required `shared-org-key` input for `obs-aw-dependency-review`可能已有人在做 @github-actions 今天认领。 未关闭
难度 1/5 1 小时以内 新手友好度 90/100
维护者通常 1 天内回复
-
bot-triaged module: inductor oncall: pt2 topic: fuzzer triaged
难度 2/5 1-3 小时 新手友好度 82/100
维护者通常 1 天内回复
-
getchaintips leaves out the active tip once a header is staged on it, where Core always lists it未关闭
难度 2/5 1-3 小时 新手友好度 88/100
btclib-org/btclib-node#2158 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 75/100
patrick-hudson/put.gd-desktop#979 · 1 条评论 ·
维护者通常 1 天内回复