Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

agentic client: venv rebuilt on every run and caller's UV_CACHE_DIR overridden

Aperta
  • Qualcosa non va?
#4,234 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
4/5
Tempo stimato
3-5 giorni
Idoneità per principianti
58/100
Tipo di issue
Bug
Chiarezza
Specificata chiaramente
Stato di attività
Attiva
Stack tecnologico
python
Ambito
backend

Direzione di ricerca

Start with infx/bench/agentic/venv.py and the existing expectations in infx/tests/bench/test_agentic_runtime.py:70-97; infx/bench/agentic/run.py:248-256 shows where bootstrap is called. Read the venv setup and tests first, then update the tests for cache selection and matching-venv reuse. Done when matching requirements avoid uv calls, changed requirements rebuild, and a caller-supplied UV_CACHE_DIR is honored.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

The agentic benchmark client rebuilds its venv on every run and ignores a caller-supplied UV_CACHE_DIR, so a caller that runs many benchmarks pays a full client download each time. Downstream: AMD-AGI/Magpie#128, AMD-AGI/Hyperloom#1919.

Current behaviour (main @ 288471b, read from code)

  • inferencex-e2e/benchmarks/srt_agentic.sh runs python3 -m infx.bench agentic, which calls venv.bootstrap when not already inside the client venv (infx/bench/agentic/run.py:248-256).
  • bootstrap always deletes the venv (infx/bench/agentic/venv.py:66), with no check of whether the existing one already matches.
  • It always sets UV_CACHE_DIR=<runtime root>/uv-cache (venv.py:67-69), overriding a value from the caller. The CI workflows set their own UV_CACHE_DIR (e.g. .github/workflows/benchmark-tmpl.yml:246), which this also overrides.
  • The runtime root is AIPERF_RUNTIME_DIR, else a per-job temp directory (venv.py:28-34). When the root is new per run, as it is for Magpie's AgentX runs, the cache is always cold and every run downloads the full client requirements again, plus uv itself if it is not on PATH (infx/bench/uv.py:21-32).
  • infx/tests/bench/test_agentic_runtime.py:70-97 pins the rebuild-and-override behaviour.

The older bash path had the same shape: 408c015 inferencex-e2e/benchmarks/benchmark_lib.sh:3133 deletes the venv and :3140-3142 force the cache path; 3d55815 made AIPERF_UV_CACHE_DIR overridable (benchmarks/benchmark_lib.sh:1787-1790) but still deleted the venv (:1841). Main dropped that override.

Impact
For a caller such as Magpie, the client starts after the server is healthy, so the download runs while the server holds its GPUs and counts against the client timeout. On a slow or restricted network a run can fail for reasons unrelated to what is being benchmarked.

Proposed change (all in infx/bench/agentic/venv.py, plus tests)

  1. Honour the caller's cache: use os.environ.get("UV_CACHE_DIR") when set, falling back to <root>/uv-cache.
  2. Reuse a matching venv: key it on PYTHON_VERSION plus the bytes of REQUIREMENTS, store the key in the venv after a successful install, and skip the rebuild when the key matches and agentx and hf are executable. Otherwise rebuild as today.
  3. If the venv is meant to be shared across concurrent runs through a persistent AIPERF_RUNTIME_DIR, take a file lock around the check-and-build.
  4. Tests: a matching key makes no uv calls; changed requirements rebuild; UV_CACHE_DIR from the caller is used.
Lingua principale
Python
Stelle
1.9k
Fork
343
Merge medio
2g 40m
PR unite (30g)
431

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di SemiAnalysisAI/InferenceX

Tutte le issue di SemiAnalysisAI/InferenceX

Issue simili

Altre issue su Python

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.