[Rebase] Rebase to vLLM 0.29.0 (#7230)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Zhou TaichangandClaude Opus 5 authored and GitHub committed 2026-09-10 12:08:28 +08:00
1 parent 333f14e97e
commit aff7d64948
120 files changed
+2958 -1690

No files matched your search

@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
from __future__ import annotations
@@ -10,12 +10,14 @@ import torch
from torch import nn
from torch.nn import functional as F
from vllm.config import AttentionConfig, CacheConfig, VllmConfig, set_current_vllm_config
from vllm.v1.kv_cache_interface import FullAttentionSpec, KVCacheConfig, KVCacheGroupSpec, KVCacheTensor
from vllm.v1.kv_cache_interface import FullAttentionSpec, KVCacheConfig, KVCacheGroupSpec
from vllm.v1.worker.gpu.attn_utils import init_attn_backend, init_kv_cache
from vllm.v1.worker.gpu.block_table import BlockTables
from tests.helpers.kv_layout import build_kv_cache_tensor
from vllm_omni.diffusion.attention.backends.abstract import AttentionMetadata
from vllm_omni.diffusion.attention.backends.flash_attn import FlashAttentionImpl
from vllm_omni.diffusion.diffusion_kv.layout import resolve_diffusion_kv_cache_layout
from vllm_omni.diffusion.diffusion_kv.paged_attention_adapter import (
DiffusionPagedAttentionAdapter,
DiffusionPagedAttentionLayerAdapter,
@@ -88,12 +90,7 @@ def test_adapter_executes_native_paged_attention_on_non_contiguous_blocks() -> N
canonical_spec = native_layer.spec
kv_cache_config = KVCacheConfig(
num_blocks=4,
kv_cache_tensors=[
KVCacheTensor(
size=canonical_spec.page_size_bytes * 4,
shared_by=[_LAYER_NAME],
)
],
kv_cache_tensors=[build_kv_cache_tensor(canonical_spec, 4, [_LAYER_NAME])],
kv_cache_groups=[
KVCacheGroupSpec(
layer_names=[_LAYER_NAME],
@@ -101,6 +98,9 @@ def test_adapter_executes_native_paged_attention_on_non_contiguous_blocks() -> N
)
],
)
# 0.29 reads the resolved physical layout when allocating; the diffusion
# control plane pins it, so this standalone harness must too.
resolve_diffusion_kv_cache_layout(vllm_config)
with set_current_vllm_config(vllm_config):
attn_groups, _, kernel_block_sizes = init_attn_backend(
kv_cache_config,
@@ -108,13 +108,13 @@ def test_adapter_executes_native_paged_attention_on_non_contiguous_blocks() -> N
device,
)
runner_kv_caches: list[torch.Tensor | list[torch.Tensor]] = []
# vLLM 0.29 dropped attn_groups and cache_dtype here: the layout now
# comes from the resolved CacheConfig.kv_cache_layout inside the call.
init_kv_cache(
runner_kv_caches,
vllm_config.compilation_config.static_forward_context,
kv_cache_config,
attn_groups,
device,
vllm_config.cache_config.cache_dtype,
kernel_block_sizes,
vllm_config,
)