History

Quantong Qiu a1da95ef44 Scale P800 long-context matrix to concurrency=1 for stability

- P800 INT8 cannot sustain >1 concurrent long-context request without OOM;
  set all scenarios to concurrency=1.
- Keep max_running=2 because max_running=1 triggers req_to_token_pool
  allocation failures in this image.
- Reduce 64k max_context_len to 72000 (65536 + 4096 + pad).
- Make run_bench.sh resilient to container death: detect dead container and
  skip remaining scenarios in the group instead of crashing the orchestrator.
- Update README to document the concurrency limitation.

2026-07-09 05:59:28 +00:00

config.env

Scale P800 long-context matrix to concurrency=1 for stability

2026-07-09 05:59:28 +00:00

README.md

Scale P800 long-context matrix to concurrency=1 for stability

2026-07-09 05:59:28 +00:00

run_bench.sh

Scale P800 long-context matrix to concurrency=1 for stability

2026-07-09 05:59:28 +00:00

start_sglang.sh

Re-enable chunked prefill for P800 long-context matrix stability

2026-07-09 05:13:04 +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