vllm
Affected
- introduced
0, fixed0.30.0(ecosystem)
Fixed versions
0.30.0
Fix
- Fixed version
0.30.0pip install --upgrade vllm==0.30.0
Advisory
Also known as: CVE-2026-105756, GHSA-2823-qmq8-rwvj
vLLM: Loose cache_salt validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream ValueError denial of service
Affected
vllmcache_salt validator and unguarded scheduling-path lookup reach.Summary
vLLM's OpenAI-compatible request models (Completions, Chat Completions, Responses) accept a client-supplied cache_salt field and validate it only as "must be a non-empty string" — no character or length restrictions. On a deployment with the built-in LMCache-MP KV connector enabled, that value is stored verbatim on the request tracker and forwarded unguarded as a keyword argument into the scheduler's per-step cache lookup. The downstream LMCache library applies a *stricter* check in IPCCacheServerKey.__post_init__, which raises ValueError for any cache_salt containing @, /, \, or NUL (or longer than 128 characters).
Neither the LMCache-MP connector lookup call site nor Scheduler.schedule() wraps that call in a request-scoped try/except, so the ValueError propagates uncaught into EngineCore's top-level handler, which treats any uncaught exception as fatal and kills the whole engine process. A single publicly reachable request with, for example, cache_salt="/" therefore takes down the engine for all concurrent users. vLLM's boundary validator is looser than the downstream consumer's, and the gap is never converted into a request-scoped failure on the scheduling path.
Affected code
Links pinned to the confirmed commit `752a3a504485` (v0.25.1):
check_cache_salt_support validators require only a non-empty string — no character or length bound: `vllm/entrypoints/openai/completion/protocol.py#L502-L508` (field at `#L172`), `vllm/entrypoints/openai/chat_completion/protocol.py#L913-L919` (field at `#L425`), and `vllm/entrypoints/openai/responses/protocol.py#L459-L465` (field at `#L235`). The loose test itself is at `completion #L503-L505`, `chat_completion #L914-L916`, `responses #L460-L462`.cache_salt with the same or weaker checking, and should be hardened at the same time: `vllm/entrypoints/pooling/base/protocol.py#L74-L85` carries the identical non-empty-string-only validator (field at `#L59`), and the token-in-token-out scale-out GenerateRequest exposes the field with no cache_salt validator at all: `vllm/entrypoints/scale_out/token_in_token_out/protocol.py#L110`.LMCacheMPRequestTracker), assignment at `#L223`.cache_salt with no surrounding try: `vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py#L733-L774` (get_num_new_matched_tokens → maybe_submit_lookup_request(...) at `#L770`).self.connector.get_num_new_matched_tokens(...), inside `schedule()` at #L396).except Exception in run_engine_core (`#L1154`) logs EngineCore encountered a fatal error., calls _send_engine_dead(), and re-raises.IPCCacheServerKey.__post_init__ in lmcache/v1/multiprocess/custom_types.py rejects @ / \ NUL and >128-char salts (_SALT_FORBIDDEN_CHARS = frozenset("@/\\\x00")) by raising ValueError.The three OpenAI check_cache_salt_support validators are identical; the completion one is representative — a non-empty-string test with no character or length bound:
# vllm/entrypoints/openai/completion/protocol.py Lines 503-509
if data.get("cache_salt") is not None and (
not isinstance(data["cache_salt"], str) or not data["cache_salt"]
):
raise VLLMValidationError(
"Parameter 'cache_salt' must be a non-empty string if provided.",
parameter="cache_salt",
)Medium Basis: CVSS v3 score 6.5, vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
0, fixed 0.30.0 (ecosystem)0.30.0
0.30.0pip install --upgrade vllm==0.30.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0