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

[Main2Main] Upgrade vLLM to 0303 (#6944)

Browse Source 
### What this PR does / why we need it?
break:
- https://github.com/vllm-project/vllm/pull/34102 
Disable_full param replaced with valid_modes/invalid_modes API
- https://github.com/vllm-project/vllm/pull/35503
Now must return float compilation_time
- https://github.com/vllm-project/vllm/pull/35564
New sequence_lengths param added
- https://github.com/vllm-project/vllm/pull/33807
A check was performed (if runner_backend != "auto")
- https://github.com/vllm-project/vllm/pull/34861
`BaseDeviceCommunicator` now accesses PyTorch's internal `pg_map` to
check process group state
- https://github.com/vllm-project/vllm/pull/35274

**Important change:**
- https://github.com/vllm-project/vllm/pull/28672

`matcher_utils` directly accesses `torch.ops._C.*` during the import
phase. In the Ascend environment, some unregistered ops trigger
`AttributeError`, causing e2e initialization failure.

https://github.com/vllm-project/vllm-ascend/actions/runs/22607260487/job/65502047131#step:10:2323

https://github.com/vllm-project/vllm/blob/main/vllm/compilation/passes/fusion/matcher_utils.py#L29

This PR adds temporary compatibility placeholders (rms_norm,
fused_add_rms_norm, rotate_embedding, static/dynamic fp8 quant,
silu_and_mul) to
`vllm_ascend/patch/platform/patch_fusion_matcher_compat_ops.py` to
ensure no crashes during the import phase. Upstream repairs will be
considered later.

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

### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Meihan-chen <jcccx.cmh@gmail.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
This commit is contained in:
SILONG ZENG
2026-03-06 09:08:52 +08:00
committed by GitHub
parent 640ecd1b77
commit bd571cf6d6
15 changed files with 87 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm_ascend/patch/platform/__init__.py
View File

@@ -17,6 +17,7 @@
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_mamba_config # noqa
import vllm_ascend.patch.platform.patch_sched_yield # noqa

24
vllm_ascend/patch/platform/patch_fusion_matcher_compat_ops.py Normal file
View File

@@ -0,0 +1,24 @@
import torch
class _MissingOp:
def __init__(self, op_name: str):
self.op_name = op_name
self.default = self
def __call__(self, *args, **kwargs):
raise RuntimeError(f"Missing upstream op `{self.op_name}` was invoked.")
def _set_missing(namespace, op_name: str, full_name: str) -> None:
if not hasattr(namespace, op_name):
setattr(namespace, op_name, _MissingOp(full_name))
_set_missing(torch.ops._C, "rms_norm", "torch.ops._C.rms_norm")
_set_missing(torch.ops._C, "fused_add_rms_norm", "torch.ops._C.fused_add_rms_norm")
_set_missing(torch.ops._C, "rotary_embedding", "torch.ops._C.rotary_embedding")
_set_missing(torch.ops._C, "static_scaled_fp8_quant", "torch.ops._C.static_scaled_fp8_quant")
_set_missing(torch.ops._C, "dynamic_scaled_fp8_quant", "torch.ops._C.dynamic_scaled_fp8_quant")
_set_missing(torch.ops._C, "dynamic_per_token_scaled_fp8_quant", "torch.ops._C.dynamic_per_token_scaled_fp8_quant")
_set_missing(torch.ops._C, "silu_and_mul", "torch.ops._C.silu_and_mul")