e8f7b2e3f1
### What this PR does / why we need it?
1. Mamba Cache Support on 310P: Implemented logic to correctly
initialize and allocate KV cache for Mamba models on the 310P platform,
including handling of state tensors and page size alignment.
2. Increased Attention Head Size Support: Modified the attention backend
to support attn_head_size larger than 128 by dynamically selecting
appropriate kernel block sizes based on hardware limitations (e.g.,
block_size * head_size <= 16384).
3. Refactored KV Cache Allocation: Consolidated and improved the KV
cache allocation mechanism, moving from separate size calculation and
allocation steps to a unified _allocate_kv_cache_tensors method that
handles both Attention and Mamba specific cache structures.
4. Dynamic Mamba Config Patching: Introduced conditional loading of
Mamba configuration patches, specifically using patch_mamba_config_310
for the 310P platform to ensure platform-specific optimizations and
validations.
5. Reserve reasonable memory to allocate KV cache to avoid OOM issue
with default gpu_memory_utilization.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Qwen3.5 E2E test
- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: pu-zhe <zpuaa@outlook.com>
34 lines
1.4 KiB
Python
34 lines
1.4 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import os
|
|
|
|
import vllm_ascend.patch.platform.patch_distributed # noqa
|
|
import vllm_ascend.patch.platform.patch_fusion_matcher_compat_ops # noqa
|
|
import vllm_ascend.patch.platform.patch_kv_cache_interface # noqa
|
|
from vllm_ascend.utils import is_310p
|
|
|
|
if not is_310p():
|
|
import vllm_ascend.patch.platform.patch_mamba_config # noqa
|
|
else:
|
|
import vllm_ascend.patch.platform.patch_mamba_config_310 # noqa
|
|
import vllm_ascend.patch.platform.patch_minimax_m2_config # noqa
|
|
import vllm_ascend.patch.platform.patch_sched_yield # noqa
|
|
import vllm_ascend.patch.platform.patch_torch_accelerator # noqa
|
|
|
|
if os.getenv("DYNAMIC_EPLB", "false").lower() in ("true", "1") or os.getenv("EXPERT_MAP_RECORD", "false") == "true":
|
|
import vllm_ascend.patch.platform.patch_multiproc_executor # noqa
|