- New experiments/p800/dsv4_p800_sglang_tp_dp_matrix: TP8/DP1, TP4/DP2, TP2/DP4 matrix with smoke results; TP2/DP4 documents the weight-loading OOM root cause (274 GiB INT8 weights sharded only across TP group). - Launch args drop --ep-size/--chunked-prefill-size/--max-prefill-tokens/ --max-running-requests; experts fall back to TP sharding. - Move dsv4_p800_256k_4k_probe under experiments/p800/. - scripts/common: jq-free parsing fixes in adaptive_bench_lib.sh and parse_backend.py. - .gitignore: cover raw_outputs under nested platform experiment layout.
48 lines
1.1 KiB
Plaintext
48 lines
1.1 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/
|
||
# 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)
|
||
datasets/
|
||
|
||
# 原始请求级输出(方案 A:极简版,不存原始 jsonl)
|
||
bench_results/**/raw_outputs/
|
||
|
||
# 实验级原始结果目录:保留 report.md / results.json,忽略原始 jsonl 和日志
|
||
# 兼容两种结构:results/<run_id>/raw_outputs/ 和 results/<run_id>/<backend>/raw_outputs/
|
||
experiments/*/results/*/raw_outputs/
|
||
experiments/*/results/*/logs/
|
||
experiments/*/results/*/*/raw_outputs/
|
||
experiments/*/results/*/*/logs/
|
||
experiments/*/results/*/*.tsv
|
||
experiments/*/results/*/*/*.tsv
|
||
# 平台子目录布局(experiments/<platform>/<name>/results/...)下的 raw_outputs
|
||
raw_outputs/
|
||
|
||
# 运行时目录(pid 文件、缓存、临时文件)
|
||
experiments/*/runtime/
|
||
|
||
# 无关项目
|
||
loomeval_yy/
|