63ab41b65a
Project-level documentation was scattered and duplicated across README.md, BENCHMARK_WORKFLOW.md, and docs/EXPERIMENT_GUIDE.md (directory layout + scripts/common component table repeated 3x). Reorganize into a clear single-source-of-truth structure. Changes: - README.md: drop the 6 stale changelog entries at the top (latest was 07-21; history lives in git log). Replace the duplicated directory- layout + scripts/common sections with a one-line link to docs/EXPERIMENT_GUIDE.md. (151 -> 99 lines) - BENCHMARK_WORKFLOW.md -> docs/BENCHMARK_WORKFLOW.md: relocate into docs/. Replace its duplicated Directory Layout and Quick Start/Adding sections with links to EXPERIMENT_GUIDE / README / NEW_PLATFORM_GUIDE; keep the unique parts (Rules, Naming Conventions, Final JSON Schema, Checklist). (394 -> 224 lines) - docs/EXPERIMENT_GUIDE.md: now the single authority for directory layout + component table + experiment conventions. Add a cross-link from the results.json field list to BENCHMARK_WORKFLOW's full JSON Schema and Naming Conventions. - docs/H200_QUICKSTART.md: deleted (outdated, repeatedly references removed legacy scripts; H200 usage is covered by ADAPTIVE_CONCURRENCY_USAGE and experiment READMEs). - docs/DSV4_INFERENCE_COMPARISON_REPORT.md -> experiments/h200/ dsv4_h200_vllm_mtp_vs_default/results/20260708-160349/: this is an experiment report, not a project doc; relocate next to its sibling report.md. - envs/ASCEND_910C_ENV_SETUP.md §8: expand the vague "pip install sglang" note into a full sglang client image build guide -- pin sglang 0.5.2 (not latest; >=0.5.16 deprecates bench_serving and breaks the parser), --no-deps minimal install loop, docker commit to a local image, with the exact commands used to build local/vllm-ascend:0.23-a3-dsv4-sglang. - experiments/h200/dsv4_h200_vllm_tp2_custom_bench/README.md: fix the now-broken link to BENCHMARK_WORKFLOW.md (../../ -> ../../../docs/). - .gitignore: ignore *.bak.glm52orig scratch backups. Also includes the add16 adaptive_results produced by the dsv4 TP=4/DP=2 runs on 910c.1.
96 lines
2.4 KiB
Plaintext
96 lines
2.4 KiB
Plaintext
# 环境/依赖/临时文件
|
||
# envs/ 目录下的虚拟环境子目录（具体环境文件不提交，但文档保留）
|
||
envs/modelscope-hub/
|
||
envs/modelscope-upload/
|
||
envs/sglang/
|
||
envs/sglang-src/
|
||
envs/vllm/
|
||
envs/charts/
|
||
# 其他一次性工具环境/临时产物
|
||
.venv-charts/
|
||
.tmp_charts/
|
||
# 其他通用忽略
|
||
deps/
|
||
tmp/
|
||
*.pid
|
||
__pycache__/
|
||
*.pyc
|
||
*.pyo
|
||
*.egg-info/
|
||
|
||
# 大文件/压缩包
|
||
*.zip
|
||
*.tar.gz
|
||
*.tar.bz2
|
||
|
||
# 中间日志
|
||
logs/
|
||
*.log
|
||
*.csv
|
||
# 数据集（可重新下载，但保留下载说明文档入库）
|
||
# 用 datasets/* 而非 datasets/，否则 !datasets/README.md 例外无法生效
|
||
datasets/*
|
||
!datasets/README.md
|
||
|
||
# 原始请求级输出与中间产物不入库：只提交 adaptive_results 下的汇总级文件
|
||
# （adaptive_points.jsonl / adaptive_shapes.jsonl / adaptive_summary.* / run_manifest.json / shapes.tsv），
|
||
# tp*_dp*/ 子目录（raw_outputs、metrics、logs、gpu_logs、server_cmd.txt）一律忽略。
|
||
experiments/*/*/adaptive_results/*/tp*_dp*/
|
||
|
||
# 实验级原始结果目录：保留 report.md / results.json / raw_outputs，忽略日志
|
||
experiments/*/results/*/logs/
|
||
experiments/*/results/*/*/logs/
|
||
experiments/*/results/*/*.tsv
|
||
experiments/*/results/*/*/*.tsv
|
||
|
||
# 运行时目录（pid 文件、缓存、临时文件）
|
||
experiments/**/runtime/
|
||
|
||
# 无关项目
|
||
loomeval_yy/
|
||
|
||
.gitignore
|
||
|
||
dsv4_dspark_h20_sglang_tp_dp_matrix
|
||
dsv4_h20_sglang_tp_dp_matrix
|
||
glm_old_h20_vllm_tp_dp_matrix
|
||
# === 仓库瘦身规范（2026-07）===
|
||
# 约定：实验目录只提交 代码(config.env/*.sh/*.py) + report.md + results.json(小体量汇总)。
|
||
# 不提交：逐请求原始日志(raw_outputs)、JIT/算子缓存、编译产物、一次性 bench 输出。
|
||
# 历史中 raw_outputs/*.jsonl 是仓库膨胀主因（~1.3GB）；本规范从源头不再入库。
|
||
# results.json 须保持小体量，禁止嵌入 raw_requests（否则单独走 raw_outputs）。
|
||
|
||
# 编译产物（每次构建重新生成）
|
||
*.o
|
||
*.so
|
||
*.ninja
|
||
*.ninja_deps
|
||
*.ninja_log
|
||
*.cubin
|
||
build/
|
||
|
||
# JIT / 算子缓存（每次跑重新生成）
|
||
sglang_sm120_cache/
|
||
vllm_sm120_cache/
|
||
*_sm120_cache/
|
||
|
||
# 一次性 bench 输出
|
||
bench-output/
|
||
|
||
# 逐请求原始日志（体积大；汇总见 results.json / report.md）
|
||
experiments/**/raw_outputs/
|
||
**/dummy_sharegpt.json
|
||
|
||
# Virtual environments (keep only docs under envs/)
|
||
envs/*
|
||
!envs/README.md
|
||
!envs/SM120_DSV4_DEPLOYMENT_GUIDE.md
|
||
!envs/ASCEND_910C_ENV_SETUP.md
|
||
!envs/UV_ENV_SETUP.md
|
||
|
||
# Tooling artifacts
|
||
skills-lock.json
|
||
|
||
# 临时备份文件
|
||
*.bak.glm52orig
|