diff --git a/vllm/envs.py b/vllm/envs.py index 02d62ecccb..160acb7009 100755 --- a/vllm/envs.py +++ b/vllm/envs.py @@ -615,6 +615,30 @@ def _resolve_rust_cli_path() -> str | None: return raw +def _e2_diagnostic_mode(name: str) -> str: + """Normalize an E2 diagnostic gate to off|warn|raise. + + One normalizer for every knob in the family, so a registry entry and the + module that acts on it cannot disagree about what the environment said. + ``1`` is accepted as ``warn`` for continuity with the earlier boolean + gates. A set-but-unrecognised value is a boot error, not a silent ``off``: + a broken gate that disarms its own instrument is the failure mode these + diagnostics exist to avoid. + """ + # An EMPTY value means off, not a boot error. Shell scripts and pytest + # fixtures both use `VAR=` to mean "unset" (see tests/v1/worker/ + # test_e2_memstats.py), and rejecting it would turn a routine way of + # clearing the variable into a crash. + value = os.environ.get(name, "off").strip().lower() or "off" + if value == "1": + return "warn" + if value not in ("off", "warn", "raise"): + raise ValueError( + f"{name} must be off|warn|raise (or 1 for warn), got {value!r}" + ) + return value + + environment_variables: dict[str, Callable[[], Any]] = { # ================== Installation Time Env Vars ================== # Target device of vLLM, supporting [cuda (by default), @@ -2193,6 +2217,23 @@ environment_variables: dict[str, Callable[[], Any]] = { "VLLM_ELASTIC_EP_DRAIN_REQUESTS": lambda: bool( int(os.getenv("VLLM_ELASTIC_EP_DRAIN_REQUESTS", "0")) ), + # PLE diagnostics. Both are off|warn|raise (1 is accepted as warn) and both + # default to off. They are registered here so the registry is the single + # source of truth for their normalization -- the modules that use them read + # these getters rather than calling os.getenv a second time, so the value + # the registry reports cannot drift from the value the check applies. + # Both are excluded from compile factors in `compile_factors` below: they + # gate HOST-side Python outside any capture and add no node to a compiled + # graph. If either ever grows a device-side component, remove it from + # `ignored_factors` in the same change. + # + # Read the pull-transport PLE semaphore back before a real launch, on the + # publishing rank only (vllm#53899 one-step-lag class). + "VLLM_E2_PLE_FLAG_CHECK": lambda: _e2_diagnostic_mode("VLLM_E2_PLE_FLAG_CHECK"), + # Host-side align row-rule and state-block collision check. + "VLLM_E2_MAMBA_SLOT_OWNERSHIP": lambda: _e2_diagnostic_mode( + "VLLM_E2_MAMBA_SLOT_OWNERSHIP" + ), # If set to 1, enable CUDA graph memory estimation during memory profiling. # This profiles CUDA graph memory usage to provide more accurate KV cache # memory allocation. Enabled by default as of v0.21.0 @@ -2340,6 +2381,13 @@ def compile_factors() -> dict[str, object]: "VLLM_DEBUG_DUMP_PATH", "VLLM_PORT", "VLLM_CACHE_ROOT", + # PLE host-side diagnostics: both gate Python that runs outside any + # capture and neither adds a node to a compiled graph, so hashing them + # would invalidate every compile cache the moment a diagnostic boot is + # taken -- which is exactly when the cache is wanted. Remove from this + # set if either ever grows a device-side component. + "VLLM_E2_PLE_FLAG_CHECK", + "VLLM_E2_MAMBA_SLOT_OWNERSHIP", # Runtime memory-plan persistence; does not affect compiled graphs. "VLLM_ENABLE_STARTUP_PLAN", # Location-only derived paths: where a cache/config directory lives