sgl-project/sglang · error · ValueError

kv-canary: expected input tensors are required when enable_w

Error message

kv-canary: expected input tensors are required when enable_write_input_assert=True

What it means

When enable_write_input_assert=True the write kernel optionally cross-checks the incoming input_ids/positions against caller-supplied expected tensors; both expected_input_tokens and expected_input_positions must then be provided. Omitting them leaves the assert mode unusable, so the launcher raises.

Source

Thrown at python/sglang/kernels/ops/kv_canary/write.py:203

    """
    canary_buf = context.canary_buf
    real_kv_sources = context.real_kv_sources
    if len(real_kv_sources) > consts.MAX_REAL_KV_SOURCES:
        raise ValueError(
            f"kv-canary: at most {consts.MAX_REAL_KV_SOURCES} RealKvSource entries supported by the CUDA ABI, "
            f"got {len(real_kv_sources)}"
        )

    _assert_contiguous(canary_buf, "canary_buf")
    _assert_contiguous(plan.write_offsets, "plan.write_offsets")
    _assert_contiguous(plan.write_seed_slot_indices, "plan.write_seed_slot_indices")
    _assert_contiguous(plan.write_num_valid_reqs, "plan.write_num_valid_reqs")
    _assert_contiguous(input_ids, "input_ids")
    _assert_contiguous(positions, "positions")
    _assert_contiguous(out_cache_loc, "out_cache_loc")
    if enable_write_input_assert:
        if expected_input_tokens is None or expected_input_positions is None:
            raise ValueError(
                "kv-canary: expected input tensors are required when enable_write_input_assert=True"
            )
        _assert_contiguous(expected_input_tokens, "expected_input_tokens")
        _assert_contiguous(expected_input_positions, "expected_input_positions")
    else:
        if expected_input_tokens is not None or expected_input_positions is not None:
            raise ValueError(
                "kv-canary: expected input tensors must be None when enable_write_input_assert=False"
            )
    _assert_contiguous(context.violation_ring, "violation_ring")
    _assert_contiguous(context.violation_write_index, "violation_write_index")
    _assert_contiguous(context.slot_run_counter, "slot_run_counter")
    _assert_contiguous(context.kernel_run_counter, "kernel_run_counter")
    _assert_contiguous(
        context.enable_chain_position_assert, "enable_chain_position_assert"
    )

    padded_bufs, source_params = _build_real_kv_source_abi(

View on GitHub (pinned to 0132848349)

Solutions

1. Pass both expected_input_tokens and expected_input_positions when enable_write_input_assert=True
2. If you do not need the cross-check, set enable_write_input_assert=False and pass neither tensor
3. Check wrapper signatures for a default of None silently dropping the tensors

Example fix

# before
launch_canary_write_kernel(ctx, plan, ..., enable_write_input_assert=True)
# after
launch_canary_write_kernel(ctx, plan, ..., enable_write_input_assert=True,
    expected_input_tokens=exp_tokens, expected_input_positions=exp_positions)

if enable_write_input_assert:
    assert expected_input_tokens is not None and expected_input_positions is not None

def assert_inputs_consistent(flag: bool, t, p) -> bool:
    return (flag and t is not None and p is not None) or (not flag and t is None and p is None)

When it happens

Trigger: Calling launch_canary_write_kernel(..., enable_write_input_assert=True) with expected_input_tokens=None or expected_input_positions=None (only one or neither supplied).

Common situations: Enabling the assert flag from config but forgetting to thread the expected tensors through a wrapper; refactoring call sites where the assert was previously off.

Understand the failure class

Background: Missing required parameter errors: what 'X is required' and 'the required X param is missing' mean, and how to fix them — this error's family across 27 libraries.

Related errors

• kv-canary: launch_canary_plan_kernels requires full_to_swa_i
• kv-canary: launch_canary_plan_kernels verify_capacity={verif
• kv-canary: launch_plan_entries_kernel requires req_to_verify
• kv-canary: write_offsets_len must be positive, got {write_of
• kv-canary: write_req_capacity must be non-negative, got {wri

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/23f24766ecda7758. Report an issue: GitHub.