EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

upgrade to 0.18.0 (#7502)

Browse Source 
### What this PR does / why we need it?
1. upgrade to 0.18.0
2. ensure kernel_block_sizes is int for Eagle drafter
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.17.0
- vLLM main:
8b6325758c

---------

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
meihanc
2026-03-21 16:05:38 +08:00
committed by GitHub
parent 80a4265717
commit bff4fbfca5
16 changed files with 139 additions and 258 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
vllm_ascend/_310p/model_runner_310p.py
View File

@@ -37,7 +37,7 @@ from vllm.v1.kv_cache_interface import (
)
from vllm_ascend.attention.attention_v1 import AscendAttentionState
from vllm_ascend.utils import ACL_FORMAT_FRACTAL_NZ, vllm_version_is
from vllm_ascend.utils import ACL_FORMAT_FRACTAL_NZ
from vllm_ascend.worker.model_runner_v1 import NPUModelRunner
from vllm_ascend.worker.npu_input_batch import NPUInputBatch
@@ -451,18 +451,11 @@ class NPUModelRunner310(NPUModelRunner):
self.kernel_block_sizes.append([0])
if block_sizes != [self.cache_config.block_size] or self.kernel_block_sizes != [[self.cache_config.block_size]]:
if vllm_version_is("0.17.0"):
assert self.cache_config.cpu_offload_gb == 0, (
"Cannot re-initialize the input batch when CPU weight "
"offloading is enabled. See https://github.com/vllm-project/vllm/pull/18298 " # noqa: E501
"for more details."
)
else:
assert self.offload_config.uva.cpu_offload_gb == 0, (
"Cannot re-initialize the input batch when CPU weight "
"offloading is enabled. See https://github.com/vllm-project/vllm/pull/18298 " # noqa: E501
"for more details."
)
assert self.offload_config.uva.cpu_offload_gb == 0, (
"Cannot re-initialize the input batch when CPU weight "
"offloading is enabled. See https://github.com/vllm-project/vllm/pull/18298 " # noqa: E501
"for more details."
)
self.input_batch = NPUInputBatch(
max_num_reqs=self.max_num_reqs,
max_model_len=max(self.model_config.max_model_len, self.max_encoder_len),