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

[Version] Drop 0.16.0 support (#7153)

Browse Source 
### What this PR does / why we need it?
Drop 0.16.0 support in main
- Fix eagle proposer break introduced by
https://github.com/vllm-project/vllm/pull/34552. Mainly change to use
the draft attention group to initialize the attention metadata builder.
- Fix the `ModelRunner` has no attribute `cudagraph_capture_sizes`
error, which is a bug in vLLM v0.17.0, and fixed by a later pr
https://github.com/vllm-project/vllm/pull/30515

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2026-03-13 16:14:15 +08:00
committed by GitHub
parent 7ed9e9de69
commit 986cd45397
20 changed files with 255 additions and 268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm_ascend/patch/worker/__init__.py
View File

@@ -17,13 +17,9 @@
from vllm.triton_utils import HAS_TRITON
from vllm_ascend.utils import vllm_version_is
if HAS_TRITON:
import vllm_ascend.patch.worker.patch_triton
if not vllm_version_is("v0.16.0"):
import vllm_ascend.patch.worker.patch_qwen3_5 # noqa
# isort: off
import vllm_ascend.patch.platform.patch_sched_yield # noqa
@@ -35,6 +31,7 @@ import vllm_ascend.patch.worker.patch_minimax_m2_linear_attn # noqa
import vllm_ascend.patch.worker.patch_multimodal_merge # noqa
import vllm_ascend.patch.worker.patch_qwen3_next # noqa
import vllm_ascend.patch.worker.patch_qwen3_next_mtp # noqa
import vllm_ascend.patch.worker.patch_qwen3_5 # noqa
import vllm_ascend.patch.worker.patch_rejection_sampler # noqa
import vllm_ascend.patch.worker.patch_v2_eagle # noqa
import vllm_ascend.patch.worker.patch_v2_uva # noqa

14
vllm_ascend/patch/worker/patch_v2_eagle.py
View File

@@ -21,14 +21,7 @@ import vllm
from vllm.v1.worker.gpu.attn_utils import build_slot_mappings_by_layer
from vllm.v1.worker.gpu.input_batch import InputBatch
from vllm.v1.worker.gpu.sample.gumbel import gumbel_sample
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("v0.16.0"):
from vllm.v1.worker.gpu.spec_decode.eagle import prepare_eagle_decode, prepare_eagle_inputs
else:
from vllm.v1.worker.gpu.spec_decode.eagle.speculator import prepare_eagle_decode, prepare_eagle_inputs
from vllm.v1.worker.gpu.spec_decode.eagle.speculator import prepare_eagle_decode, prepare_eagle_inputs
from vllm_ascend.worker.v2.attn_utils import build_attn_metadata
@@ -175,7 +168,4 @@ def propose(
return self.draft_tokens[:num_reqs]
if vllm_version_is("v0.16.0"):
vllm.v1.worker.gpu.spec_decode.eagle.EagleSpeculator.propose = propose
else:
vllm.v1.worker.gpu.spec_decode.eagle.speculator.EagleSpeculator.propose = propose
vllm.v1.worker.gpu.spec_decode.eagle.speculator.EagleSpeculator.propose = propose