Skip to content

agentx-standalone.md

Latest commit

 

History

History
75 lines (59 loc) · 2.92 KB

agentx-standalone.md

File metadata and controls

75 lines (59 loc) · 2.92 KB
Raw

Run AgentX-Harness Standalone

Run the AgentX client against an already-running OpenAI-compatible server.

Install

Install the pinned PyPI release in a Python 3.11–3.13 virtual environment:

python3 -m venv .venv-agentx
source .venv-agentx/bin/activate
python -m pip install 'agentx-harness==1.0.12'

The package version matches the agentx-v1.0.12 GitHub release. The agentx command selects the agentx scenario by default.

Run

set -eo pipefail
SERVER_URL="http://127.0.0.1:8000"
SERVED_MODEL_NAME="moonshotai/Kimi-K3"
TOKENIZER="moonshotai/Kimi-K3"
DATASET="semianalysis_cc_traces_weka_062126"
CONC=8
OUTPUT_DIR="$PWD/results/agentx-c${CONC}-$(date -u +%Y%m%dT%H%M%SZ)"

mkdir -p "$OUTPUT_DIR"
agentx profile \
  --url "$SERVER_URL" --endpoint /v1/chat/completions \
  --model "$SERVED_MODEL_NAME" --tokenizer "$TOKENIZER" \
  --tokenizer-trust-remote-code \
  --concurrency "$CONC" \
  --public-dataset "$DATASET" \
  --output-artifact-dir "$OUTPUT_DIR/aiperf_artifacts" \
  2>&1 | tee "$OUTPUT_DIR/aiperf.log"

The agentx preset supplies a one-hour profile, ten warmup requests per lane, and shared reporting and runtime settings. Explicit CLI arguments and AIPERF_* environment variables override preset defaults. Model, tokenizer, dataset, concurrency, and output remain caller inputs; --tokenizer-trust-remote-code is needed only for tokenizers with custom code.

InferenceX's python3 -m infx.bench agentic wrapper defaults to the full, uncapped corpus (semianalysis_cc_traces_weka_062126). Model prefixes beginning with dsr1, qwen3.5, or qwen3.8next explicitly select the 256k-capped corpus (semianalysis_cc_traces_weka_062126_256k). New model families use the full corpus unless added to CAPPED_FAMILIES in infx/bench/agentic/traces.py. WEKA_LOADER_OVERRIDE can pin either loader regardless of model family; it does not configure the standalone agentx CLI.

The default random seed is 42. Keep this seed when reproducing AgentX results, or pass --random-seed 123 to use a different seed.

Allow additional time for dataset preparation, warmup, and draining requests. To sweep, restart the server for every CONC value and use a fresh output directory. Do not flush caches or reuse a live server across concurrency points. Match the target recipe's duration and warmup settings when reproducing a result.

Add --server-metrics "${SERVER_URL}/metrics" if the server exposes metrics.

Optional session-affinity flags

For DP-attention runs requiring router affinity, export these before agentx profile. They add headers without replacing X-Correlation-ID.

# Adds X-Dynamo-Session-ID; subagents also get X-Dynamo-Parent-Session-ID.
# Only this option sends the parent ID, preserving forked-agent lineage.
export AIPERF_HTTP_X_DYNAMO_SESSION_ID_FROM_CORRELATION_ID=true
# Also sends X-Session-ID, if a front-end router needs it.
export AIPERF_HTTP_X_SESSION_ID_FROM_CORRELATION_ID=true