History

SSKJ Dev a4e38b9e33 Reorganize experiments into hardware-specific subdirectories

Move all experiments under hardware-specific folders:
- experiments/h200/     : H200 GPU experiments (15 dirs)
- experiments/h20/      : H20 GPU experiments (2 dirs)
- experiments/p800/     : Kunlun P800 experiments (3 dirs)
- experiments/pro6000/    : RTX 6000D experiments (2 dirs)

This improves discoverability and keeps hardware-specific configs
isolated from each other.

2026-07-16 04:11:07 +00:00

config.env

Reorganize experiments into hardware-specific subdirectories

2026-07-16 04:11:07 +00:00

README.md

Reorganize experiments into hardware-specific subdirectories

2026-07-16 04:11:07 +00:00

run_bench.sh

Reorganize experiments into hardware-specific subdirectories

2026-07-16 04:11:07 +00:00

start_sglang.sh

Reorganize experiments into hardware-specific subdirectories

2026-07-16 04:11:07 +00:00

README.md

P800 Long-Context Matrix for DeepSeek-V4-Flash-INT8

Long-context throughput/latency matrix for SGLang-XPU on Kunlun P800 (8x XPU).

Scope

Model: DeepSeek-V4-Flash-INT8 (W8A8 INT8)
Backend/engine: sglang-xpu
Hardware: 8x Kunlun P800 XPU
Input lengths: 64k, 128k
Output lengths: 256, 1024, 4096
Concurrency: 1 — P800 INT8 can only sustain one concurrent long-context request without OOM; max_running=2 is kept because max_running=1 triggers req_to_token_pool allocation failures in this image.

Usage

cd /data1/yy/sskj/experiments/dsv4_p800_long_context_matrix
bash run_bench.sh

Optional environment overrides:

PORT=30013 RUN_ID=myrun bash run_bench.sh

Outputs

Results are saved under results/${RUN_ID}/:

raw_outputs/: raw sglang.bench_serving JSONL files
report.md: parsed per-scenario metrics
results.json: structured metadata + scenarios