qqtang/sskj
1
2
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
sskj/experiments/dsv4_p800_long_context_matrix/README.md
Quantong Qiu 90eecc4ede Add P800 long-context matrix experiment (64k/128k) for DeepSeek-V4-Flash-INT8 
- New experiment: experiments/dsv4_p800_long_context_matrix/
- Single backend: sglang-xpu in Docker on Kunlun P800
- Context groups: 64k (max_context_len=80000, max_running=10) and
  128k (max_context_len=140000, max_running=5)
- Scenarios: concurrency sweeps x output lengths 256/1024/4096
- Parameterized start_sglang.sh enforces max_running >= 2 to avoid
  P800 INT8 req_to_token_pool allocation failures
- Reuses proven P800 INT8 environment, NSA/EAGLE settings, and
  bench_serving invocations from dsv4_p800_max_context_length
2026-07-09 04:45:04 +00:00

772 B
Raw Blame History

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: sweeps per context group (see config.env)

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