- Document the rule in docs/EXPERIMENT_GUIDE.md section 7
- Update all config.env SCENARIOS to follow the 5x rule
- Migrate dsv4_h200_sglang, dsv4_h200_vllm, dsv4_p800_sglang
from global NUM_PROMPTS to per-scenario num_prompts
- Keep long-context phase2 as exception (low counts documented)
- Add legacy 3-field fallback in run_bench.sh loops
These were failed/intermediate smoke-test runs created while debugging the
managed server startup. Keep the repository clean; new runs can be reproduced
with experiments/dsv4_p800_sglang/run_bench.sh.
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.
start_server.sh referenced LOG_DIR and RESULT_ROOT without defining them,
causing an unbound-variable failure under set -u. Mirror the initialization
from run_bench.sh so the script can run standalone.
- Remove USE_FAST_BFP16_MOE=1 which caused torch parameter assignment
crash in fresh containers for w8a8_int8 mode.
- Mount model path at its host absolute path inside the container so the
bench client tokenizer can load it regardless of server --model-path.
- Default WARMUP to 0 and NUM_PROMPTS to 10 for a fast smoke test.
- Default to a single scenario; document how to run a full grid.
- Update experiment README with PLATFORM env var and override examples.
