31a21631b8
parse_jsonl 当 raw 文件是单个聚合 JSON 对象时返回 [data](整个聚合含 itls/generated_texts 数组)，原代码把它当 raw_requests[:100] 塞进 scenario， 导致单次 bench 的 results.json 膨胀到 12.5MB(itls 6.95MB + generated_texts 1.54MB)。 而真正有用的聚合百分位已在 latencies 字段(~0.5KB)，逐请求原始数据已在 raw_outputs/*.jsonl，raw_requests 字段纯冗余。 - 移除 scenario dict 的 raw_requests 字段; parse_jsonl 返回值改用 _ 接收 - 符合 BENCHMARK_WORKFLOW.md: 产生大量请求时逐请求数据存 raw_outputs, results.json 只留聚合百分位 - 实测 qwen3_235b results.json: 12.52MB -> ~KB - 同步修改 4 份相同 md5 的 parse_results.py(本提交含 3 份 tracked; qwen3_8b 未跟踪待随实验提交) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
DSV4 P800 256k-Input / 4k-Output Probe
Kunlun P800 XPU + SGLang + DeepSeek-V4-Flash-INT8 long-context OOM probe.
What it does
Sends 4 prompts with 262144 input tokens and requests 4096 output tokens at concurrency=2, then checks whether the server completes the scenario without OOM or context-length errors.
Quick Start
Against an already-running server (recommended on shared P800 machines)
PLATFORM=kunlun_p800 \
SKIP_MANAGE_SERVER=1 \
PORT=30000 \
bash experiments/p800/dsv4_p800_256k_4k_probe/run_bench.sh
Standalone (starts its own Docker container)
PLATFORM=kunlun_p800 \
bash experiments/p800/dsv4_p800_256k_4k_probe/run_bench.sh
This will start a fresh sglang-dsv4-flash container with the baseline
w8a8_int8 launch args (no EAGLE speculative decoding), plus
--context-length 270000 --max-running-requests 4, and tear it down on exit.
To use the tuned config with EAGLE speculative decoding instead:
SERVER_MODE=w8a8_int8 PLATFORM=kunlun_p800 \
bash experiments/p800/dsv4_p800_256k_4k_probe/run_bench.sh
Configuration
Edit config.env or override via environment variables:
# Use a different port or model path
PORT=30001 \
MODEL_PATH=/data1/models/DeepSeek-V4-Flash-INT8 \
PLATFORM=kunlun_p800 \
bash experiments/p800/dsv4_p800_256k_4k_probe/run_bench.sh
Files
| File | Purpose |
|---|---|
config.env |
Experiment-level configuration (model, port, scenario) |
start_server.sh |
Start the P800 SGLang Docker container with 256k context args |
run_bench.sh |
Orchestrator: server → warmup → probe scenario → stop server |
parse_results.py |
Parse logs and generate results.json + report.md |
Platform
This experiment targets platforms/kunlun_p800.env.