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

Main2main upgrade to vllm 0317 afternoon (#7409)

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

1.fix "TypeError: get_attn_backend() remove variable": [Refactor
`check_and_update_config`](https://github.com/vllm-project/vllm/pull/35122)

2.fix [Rename `compile_ranges_split_points` to
`compile_ranges_endpoints`](https://github.com/vllm-project/vllm/pull/36027)

3.fix "RuntimeError: device_allocator not a DeviceAllocator":[Replace
memory related torch.cuda
APIs"](https://github.com/vllm-project/vllm/pull/37031)

4.fix [Support multiple KV groups in OffloadingSpec
](https://github.com/vllm-project/vllm/pull/36610) removed
self.offloaded_block_size and changed self.gpu_block_size from a scalar
to a tuple of per-group block sizes, adding block_size_factor.

5.fix [Consolidate
SupportsEagle](https://github.com/vllm-project/vllm/pull/36063) renamed
get_eagle3_aux_hidden_state_layers() to
get_eagle3_default_aux_hidden_state_layers() and added a
supports_eagle3() guard before calling it.

### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
E2E


- vLLM version: v0.17.0
- vLLM main:
8a680463fa

---------

Signed-off-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
This commit is contained in:
Nengjun Ma
2026-03-18 23:24:27 +08:00
committed by GitHub
parent 305820f1a9
commit 8b79d4de52
13 changed files with 125 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
vllm_ascend/ascend_config.py
View File

@@ -181,30 +181,47 @@ class AscendConfig:
stacklevel=2,
)
@staticmethod
def _get_compile_ranges(compilation_config):
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("0.17.0"):
return compilation_config.compile_ranges_split_points
else:
return compilation_config.compile_ranges_endpoints
@staticmethod
def _set_compile_ranges(compilation_config, value):
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("0.17.0"):
compilation_config.compile_ranges_split_points = value
else:
compilation_config.compile_ranges_endpoints = value
def update_compile_ranges_split_points(self):
vllm_config = self.vllm_config
if self.ascend_compilation_config.enable_npugraph_ex:
if self.ascend_compilation_config.fuse_allreduce_rms:
from vllm_ascend.compilation.passes.allreduce_rmsnorm_fusion_pass import ALLREDUCE_NORM_FUSE_THRESHOLD
new_compile_ranges_split_points = vllm_config.compilation_config.compile_ranges_split_points
new_compile_ranges_split_points = self._get_compile_ranges(vllm_config.compilation_config)
new_compile_ranges_split_points.append(ALLREDUCE_NORM_FUSE_THRESHOLD)
new_compile_ranges_split_points = sorted(new_compile_ranges_split_points)
vllm_config.compilation_config.compile_ranges_split_points = new_compile_ranges_split_points
self._set_compile_ranges(vllm_config.compilation_config, new_compile_ranges_split_points)
logger.debug(
"set compile_ranges_split_points to "
"{new_compile_ranges_split_points} for matmul and allreduce fusion"
)
else:
new_compile_ranges_split_points = vllm_config.compilation_config.compile_ranges_split_points
new_compile_ranges_split_points = self._get_compile_ranges(vllm_config.compilation_config)
if vllm_config.additional_config.get("ascend_compilation_config", {}).get("fuse_allreduce_rms", True):
from vllm_ascend.compilation.passes.allreduce_rmsnorm_fusion_pass import ALLREDUCE_NORM_FUSE_THRESHOLD
new_compile_ranges_split_points = vllm_config.compilation_config.compile_ranges_split_points
new_compile_ranges_split_points.append(ALLREDUCE_NORM_FUSE_THRESHOLD)
new_compile_ranges_split_points = sorted(new_compile_ranges_split_points)
vllm_config.compilation_config.compile_ranges_split_points = new_compile_ranges_split_points
self._set_compile_ranges(vllm_config.compilation_config, new_compile_ranges_split_points)
logger.debug(
"set compile_ranges_split_points to "
"{new_compile_ranges_split_points} for matmul and allreduce fusion"
@@ -218,9 +235,9 @@ class AscendConfig:
sp_threshold = get_sp_threshold(vllm_config)
new_compile_ranges_split_points.append(sp_threshold)
logger.debug(f"add {sp_threshold} to compile_ranges_split_points for sequence parallelism")
if len(new_compile_ranges_split_points) > len(vllm_config.compilation_config.compile_ranges_split_points):
if len(new_compile_ranges_split_points) > len(self._get_compile_ranges(vllm_config.compilation_config)):
new_compile_ranges_split_points = sorted(new_compile_ranges_split_points)
vllm_config.compilation_config.compile_ranges_split_points = new_compile_ranges_split_points
self._set_compile_ranges(vllm_config.compilation_config, new_compile_ranges_split_points)
class FinegrainedTPConfig: