[Mamba] RecoverSSM align: keep a boundary-ending state in its block

A speculative window whose accepted tokens end exactly on a recurrent block
boundary selected the following block-table column for the committed state
(commit plan) and recorded it as the running column (postprocess). That
column can still be unallocated, so the next step reads an uninitialized
page. Select the block that holds the last committed token, matching the
(n - 1) // block convention used elsewhere in align mode. Applies to
Kimi-K3 KDA and to the Qwen GDN/PLE RecoverSSM paths that share the plan.

Fix and test from local-inference-lab/vllm a02f585d (Martin Vit, root cause
reported by astra); the GDN/PLE align tests now expect the same convention.

Signed-off-by: Jürgen Schmied <juergenschmied70@gmail.com>
Co-authored-by: Martin Vit <martin@voipmonitor.org>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Jürgen Schmied
2026-09-27 11:12:40 +02:00
co-authored by Martin Vit Claude
parent ed2a9665ea
commit 5567cc1b25
5 changed files with 143 additions and 7 deletions
+5 -4
View File
@@ -299,14 +299,15 @@ def test_commit_maps_noncontiguous_requests_in_align_mode():
for i, r in enumerate(req_rows.tolist()):
n = min(int(acc[r]), qlens[i])
c0 = int(nc[r])
final_blk = int(bt[r, (c0 + n) // bs])
final_blk = int(bt[r, max(c0 + n - 1, 0) // bs])
tok = int(inp["query_start_loc"][i]) + n - 1
torch.testing.assert_close(ckpt[final_blk], states[tok], rtol=1e-5, atol=1e-6)
# (num_computed, accepted, block size): boundary after 1 / after 2 / ending exactly on
# it / crossing and continuing / accepted = 1 without crossing / the full window
# crossing after 3
# crossing after 3. A window ending exactly on a boundary keeps its state in the block
# holding its last token: the next block may still be unallocated.
ALIGN_CASES = [
(3, 2, 4),
(2, 3, 4),
@@ -338,7 +339,7 @@ def test_align_boundary_and_final_state_match_native(nc, accepted, bs):
mamba_block_size=bs,
)
next_boundary = (nc // bs + 1) * bs
final_blk = int(bt[0, (nc + accepted) // bs])
final_blk = int(bt[0, max(nc + accepted - 1, 0) // bs])
if (
nc + accepted >= next_boundary
): # crosses: the boundary state goes into the source block
@@ -585,7 +586,7 @@ def test_align_boundary_bf16_state(nc, accepted, bs):
mamba_block_size=bs,
)
next_boundary = (nc // bs + 1) * bs
final_blk = int(bt[0, (nc + accepted) // bs])
final_blk = int(bt[0, max(nc + accepted - 1, 0) // bs])
if nc + accepted >= next_boundary:
torch.testing.assert_close(
ckpt[int(src)].float(),
+1 -1
View File
@@ -124,7 +124,7 @@ def test_ple_commit_align_boundary(num_computed, accepted, crosses):
mamba_block_size=block_size,
)
final_block = nxt if num_computed + accepted >= block_size else src
final_block = nxt if num_computed + accepted > block_size else src
assert torch.equal(view[final_block, :, :STATE_LEN], want_final)
if crosses:
assert torch.equal(view[src, :, :STATE_LEN], want_boundary)
@@ -0,0 +1,129 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Align-mode RecoverSSM state columns at recurrent block boundaries.
A speculative window whose accepted tokens end exactly on a recurrent block
boundary must keep its state in the block holding the last committed token.
The following block can still be unallocated, so selecting it would drop the
commit while the bookkeeping recorded the state as advanced.
"""
import pytest
import torch
from vllm.models.kimi_k3.nvidia.ops.recoverssm import _prepare_commit_plan_kernel
from vllm.platforms import current_platform
from vllm.v1.attention.backends.utils import NULL_BLOCK_ID
from vllm.v1.worker.gpu.model_states.recoverssm import (
_postprocess_recoverssm_align_kernel,
)
pytestmark = pytest.mark.skipif(
not current_platform.is_cuda_alike(),
reason="The RecoverSSM kernels require a CUDA-alike device.",
)
BLOCK_SIZE = 2048
SPEC_QUERY_LEN = 4
BLOCKS = [100, 101, 102, 103, 104, 105]
# (computed before the step, committed tokens, allocated block columns,
# final column, boundary column or None)
CASES = [
# 8,188 + 4 ends exactly on the 8,192 boundary; column 4 is unallocated.
(8188, 4, 4, 3, 3),
# The window crosses the boundary: state moves on, checkpoint stays behind.
(8190, 4, 5, 4, 3),
# The window stays inside column 3.
(8180, 4, 4, 3, None),
# The first token after a boundary belongs to the new column.
(8192, 1, 5, 4, None),
# Single-token commit ending on the first boundary.
(2047, 1, 1, 0, 0),
]
@pytest.mark.parametrize(
"num_computed,commit_len,allocated,final_col,boundary_col", CASES
)
def test_commit_plan_keeps_boundary_state_in_last_computed_block(
num_computed, commit_len, allocated, final_col, boundary_col
):
device = current_platform.device_type
columns = [
block if col < allocated else NULL_BLOCK_ID for col, block in enumerate(BLOCKS)
]
block_table = torch.tensor([columns], dtype=torch.int32, device=device)
num_accepted = torch.tensor([commit_len], dtype=torch.int32, device=device)
state_indices = torch.tensor(
[BLOCKS[(num_computed - 1) // BLOCK_SIZE]], dtype=torch.int32, device=device
)
query_start_loc = torch.tensor(
[0, SPEC_QUERY_LEN], dtype=torch.int32, device=device
)
computed = torch.tensor([num_computed], dtype=torch.int32, device=device)
commit_lens, final_indices, boundary_indices, recovery_lens = (
torch.full((1,), -7, dtype=torch.int32, device=device) for _ in range(4)
)
_prepare_commit_plan_kernel[(1,)](
num_accepted,
None,
state_indices,
query_start_loc,
block_table,
computed,
commit_lens,
final_indices,
boundary_indices,
recovery_lens,
NULL_BLOCK_ID,
BLOCK_SIZE,
block_table.shape[1],
num_accepted.stride(0),
0,
state_indices.stride(0),
query_start_loc.stride(0),
block_table.stride(0),
block_table.stride(1),
computed.stride(0),
SPEC_QUERY_LEN=SPEC_QUERY_LEN,
num_warps=1,
)
assert commit_lens.item() == commit_len
assert final_indices.item() == BLOCKS[final_col]
expected_boundary = NULL_BLOCK_ID if boundary_col is None else BLOCKS[boundary_col]
assert boundary_indices.item() == expected_boundary
if boundary_col is not None:
next_boundary = (num_computed // BLOCK_SIZE + 1) * BLOCK_SIZE
assert recovery_lens.item() == next_boundary - num_computed
@pytest.mark.parametrize(
"num_computed,commit_len,allocated,final_col,boundary_col", CASES
)
def test_postprocess_records_the_committed_state_column(
num_computed, commit_len, allocated, final_col, boundary_col
):
device = current_platform.device_type
idx_mapping = torch.tensor([2], dtype=torch.int32, device=device)
num_sampled = torch.tensor([commit_len], dtype=torch.int32, device=device)
computed = torch.tensor([num_computed], dtype=torch.int32, device=device)
state_idx = torch.full((4,), -7, dtype=torch.int32, device=device)
num_accepted = torch.full((4,), -7, dtype=torch.int32, device=device)
_postprocess_recoverssm_align_kernel[(1,)](
idx_mapping,
num_sampled,
None,
computed,
state_idx,
num_accepted,
MAMBA_BLOCK_SIZE=BLOCK_SIZE,
BLOCK_TABLE_WIDTH=len(BLOCKS),
)
assert state_idx[2].item() == final_col
assert num_accepted[2].item() == 1
assert state_idx[[0, 1, 3]].tolist() == [-7, -7, -7]
@@ -78,8 +78,12 @@ def prepare_commit_plan_kernel(
tl.int32
)
final_num_computed = num_computed + commit_len
# The committed state belongs to the block holding the last committed
# token. A window ending exactly on a boundary stays in that block; the
# next block may still be unallocated.
final_state_col = tl.minimum(
final_num_computed // mamba_block_size, block_table_width - 1
tl.maximum(final_num_computed - 1, 0) // mamba_block_size,
block_table_width - 1,
)
final_state_idx = tl.load(
block_table_ptr
@@ -91,10 +91,12 @@ def _postprocess_recoverssm_align_kernel(
return
num_sampled = tl.load(num_sampled_ptr + batch_idx)
num_computed = tl.load(num_computed_ptr + batch_idx)
# Match the commit plan: the running state lives in the block holding the
# last computed token, so the next step migrates it across a boundary.
tl.store(
state_idx_ptr + req_state_idx,
tl.minimum(
(num_computed + num_sampled) // MAMBA_BLOCK_SIZE,
tl.maximum(num_computed + num_sampled - 1, 0) // MAMBA_BLOCK_SIZE,
BLOCK_TABLE_WIDTH - 1,
),
)