vllm-project/vllm · error · ValueError
Input list lengths mismatch
Error message
Input list lengths mismatch
What it means
Error "Input list lengths mismatch" thrown in vllm-project/vllm.
Source
Thrown at vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connector.py:2423
remote_block_ids=meta.remote_block_ids,
layer_name=layer_name,
kv_layer=kv_layer,
remote_notify_port=meta.remote_notify_port,
remote_ip=meta.remote_host,
)
def merge_contiguous_blocks(
self,
offsets_local: list[int],
offsets_remote: list[int],
sizes: list[int],
assume_sorted: bool = False,
) -> tuple[list[int], list[int], list[int]]:
n = len(offsets_local)
if n == 0:
return [], [], []
if not (n == len(offsets_remote) == len(sizes)):
raise ValueError("Input list lengths mismatch")
local_arr = np.fromiter(offsets_local, dtype=np.int64, count=n)
remote_arr = np.fromiter(offsets_remote, dtype=np.int64, count=n)
sizes_arr = np.fromiter(sizes, dtype=np.int64, count=n)
if assume_sorted:
local_sorted = local_arr
remote_sorted = remote_arr
sizes_sorted = sizes_arr
else:
if np.all(local_arr[:-1] <= local_arr[1:]):
local_sorted = local_arr
remote_sorted = remote_arr
sizes_sorted = sizes_arr
else:
sort_idx = np.argsort(local_arr, kind="stable")
local_sorted = local_arr[sort_idx]
remote_sorted = remote_arr[sort_idx]
sizes_sorted = sizes_arr[sort_idx]View on GitHub (pinned to c794754062)
Solutions
- Ensure all input lists passed to the MoRIIO transfer have equal lengths.
When it happens
Trigger: Raised at vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connector.py:2423 when validation fails: Input list lengths mismatch. Typically triggered by an incompatible or incomplete vLLM configuration, an unsupported platform/backend combination, or a runtime resource/dependency that is missing.
Common situations: Commonly encountered at vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connector.py:2423 during vLLM startup/config validation or runtime setup when: (1) conflicting CLI flags or config fields are combined, (2) the current platform (CUDA/ROCm/CPU/XPU) or installed optional packages do not support the requested feature, or (3) a required value is absent or out of range. Resolve by correcting the configuration as described in the message, or by selecting a supported alternative.
AI-assisted analysis of vllm-project/vllm@c794754062 (2026-08-14).
Data as JSON: /api/errors/f083d6ec25ef4b54.
Report an issue: GitHub.