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

[Main2Main] Upgrade vLLM to 0226 (#6813)

Browse Source 
### What this PR does / why we need it?

Breaking:
1. https://github.com/vllm-project/vllm/pull/33452
2. https://github.com/vllm-project/vllm/pull/33451
3. https://github.com/vllm-project/vllm/pull/32567
4. https://github.com/vllm-project/vllm/pull/32344

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
83b47f67b1

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
Canlin Guo
2026-02-27 16:05:21 +08:00
committed by GitHub
parent 80316c5824
commit e4458b2d2b
40 changed files with 117 additions and 184 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm_ascend/compilation/passes/allreduce_rmsnorm_fusion_pass.py
View File

@@ -16,6 +16,8 @@
#
import torch
from torch._inductor.pattern_matcher import Match, PatternMatcherPass, PatternPrettyPrinter
from vllm.compilation.passes.inductor_pass import get_pass_context
from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
from vllm.config import VllmConfig
from vllm.config.compilation import Range
from vllm.distributed import get_tensor_model_parallel_world_size, tensor_model_parallel_all_reduce
@@ -24,14 +26,6 @@ from vllm.logger import logger
from vllm_ascend.compilation.passes.base_pattern import BasePattern
from vllm_ascend.compilation.passes.utils.npugraph_ex_utils_check import extra_stream_scope_check
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("0.15.0"):
from vllm.compilation.inductor_pass import get_pass_context # type: ignore
from vllm.compilation.vllm_inductor_pass import VllmInductorPass # type: ignore
else:
from vllm.compilation.passes.inductor_pass import get_pass_context
from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
# computation-communication tiling block is 512
ALLREDUCE_NORM_FUSE_THRESHOLD = 512

8
vllm_ascend/compilation/passes/norm_quant_fusion_pass.py
View File

@@ -17,17 +17,13 @@
#
import torch
from torch._inductor.pattern_matcher import PatternMatcherPass
from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
from vllm.config import VllmConfig
from vllm.config.compilation import Range
from vllm.logger import logger
from vllm_ascend.compilation.passes.base_pattern import BasePattern
from vllm_ascend.utils import enable_custom_op, vllm_version_is
if vllm_version_is("0.15.0"):
from vllm.compilation.vllm_inductor_pass import VllmInductorPass # type: ignore
else:
from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
from vllm_ascend.utils import enable_custom_op
class AddRMSNormQuantPattern(BasePattern):

10
vllm_ascend/compilation/passes/qknorm_rope_fusion_pass.py
View File

@@ -17,19 +17,13 @@
#
import torch
from torch._inductor.pattern_matcher import PatternMatcherPass, PatternPrettyPrinter
from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
from vllm.config import VllmConfig, get_layers_from_vllm_config
from vllm.config.compilation import Range
from vllm.logger import logger
from vllm.model_executor.layers.attention import Attention
from vllm_ascend.compilation.passes.base_pattern import BasePattern
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("v0.15.0"):
from vllm.attention.layer import Attention # type: ignore
from vllm.compilation.vllm_inductor_pass import VllmInductorPass # type: ignore
else:
from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
from vllm.model_executor.layers.attention import Attention
class QKNormRopeFusionPattern(BasePattern):