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

[Misc] Remove VLLM_USE_V1 usage in code (#1764)

Browse Source 
We plan to remove V0 code from this version. The first step is to delete
v0 usage.

Related: https://github.com/vllm-project/vllm-ascend/issues/1620

- vLLM version: v0.9.2
- vLLM main:
61e20828da

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-07-15 11:52:16 +08:00
committed by GitHub
parent 494b0f474f
commit 7bdada58eb
6 changed files with 100 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
vllm_ascend/ascend_config.py
View File

@@ -15,7 +15,6 @@
# limitations under the License.
from typing import Optional
import vllm.envs as envs
from vllm.logger import logger
TORCHAIR_MODEL_LIST = ["deepseek", "pangu"]
@@ -126,46 +125,36 @@ def get_ascend_config():
def check_ascend_config(vllm_config, enforce_eager):
ascend_config = get_ascend_config()
# for v0 engine
if not envs.VLLM_USE_V1:
# for eager mode
if enforce_eager:
# torchair_graph cannot be enabled with eager mode.
if ascend_config.torchair_graph_config.enabled:
raise NotImplementedError(
"Torchair graph mode is only supported for V1 Engine.")
if ascend_config.ascend_scheduler_config.enabled:
raise NotImplementedError(
"Ascend scheduler is only supported for V1 Engine.")
# for v1 engine
raise RuntimeError(
"Can't enable graph mode and eager mode at the same time. Please set `enforce_eager=False` if you attempt to enable NPU graph mode."
)
# for graph mode
else:
# for eager mode
if enforce_eager:
# torchair_graph cannot be enabled with eager mode.
if ascend_config.torchair_graph_config.enabled:
raise RuntimeError(
"Can't enable graph mode and eager mode at the same time. Please set `enforce_eager=False` if you attempt to enable NPU graph mode."
)
# for graph mode
# torchair_graph case
if ascend_config.torchair_graph_config.enabled:
# torchair_graph is supported for deepseek/pangu model only.
if vllm_config.model_config:
model_type = vllm_config.model_config.hf_config.model_type
if not _check_torchair_supported(model_type):
raise NotImplementedError(
"Torchair graph mode only works with following model types:"
f"{TORCHAIR_MODEL_LIST}.")
# aclgraph case
else:
# torchair_graph case
if ascend_config.torchair_graph_config.enabled:
# torchair_graph is supported for deepseek/pangu model only.
if vllm_config.model_config:
model_type = vllm_config.model_config.hf_config.model_type
if not _check_torchair_supported(model_type):
raise NotImplementedError(
"Torchair graph mode only works with following model types:"
f"{TORCHAIR_MODEL_LIST}.")
# aclgraph case
else:
# aclgraph doesn't work with deepseek model and only qwen model is well tested.
if vllm_config.model_config:
model_type = vllm_config.model_config.hf_config.model_type
if "deepseek" in model_type:
raise NotImplementedError(
"ACL Graph does not support deepseek. Please "
"try torchair graph mode to serve deepseek models on vllm-ascend."
" Or set `enforce_eager=True` to use eager mode.")
if "qwen" not in model_type:
logger.warning(
"ACL Graph is currently experimental. Please "
"raise an issue on https://github.com/vllm-project/vllm-ascend/issues"
" if you encourage any Error")
# aclgraph doesn't work with deepseek model and only qwen model is well tested.
if vllm_config.model_config:
model_type = vllm_config.model_config.hf_config.model_type
if "deepseek" in model_type:
raise NotImplementedError(
"ACL Graph does not support deepseek. Please "
"try torchair graph mode to serve deepseek models on vllm-ascend."
" Or set `enforce_eager=True` to use eager mode.")
if "qwen" not in model_type:
logger.warning(
"ACL Graph is currently experimental. Please "
"raise an issue on https://github.com/vllm-project/vllm-ascend/issues"
" if you encourage any Error")