qqtang/sskj
1
2
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
sskj/experiments/dsv4_p800_sglang/results/20260708-051023/report.md
Quantong Qiu 3694614dd9 feat(p800): add max context length exploration experiment 
Add experiments/dsv4_p800_max_context_length/ to find the longest input
context that P800 SGLang INT8 can serve for DeepSeek-V4-Flash-INT8.

- Docker-based server start with dynamic --context-length.
- Single-request, single-output-token probes for each candidate length.
- Records success/failure, server args, and metrics per length.
- Generates results.json and report.md summarizing the max supported length.
- Smoke-tested at 4096 tokens successfully.
2026-07-09 03:30:09 +00:00

526 B
Raw Blame History

Benchmark Report: dsv4_p800_sglang

Metadata

  • Run ID: 20260708-051023
  • Timestamp: 2026-07-08T05:10:23+00:00
  • Chip/Accelerator: Kunlun P800 XPU / kunlun_p800
  • Engine/Backend: sglang-xpu / sglang
  • Hardware: 8x Kunlun P800 XPU
  • Model: /data1/models/DeepSeek-V4-Flash-INT8
  • Git Commit: 2c332ff

Results

Scenario Conc In/Out Success Failed Req/s OutTok/s TTFT p50 TTFT p99 TPOT p50 TPOT p99 E2E p99