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

[CI] Remove compatibility maintenance for vllm v0.10.1 and v0.10.1.1 (#2840)

Browse Source 
### What this PR does / why we need it?
Remove compatibility maintenance for vllm v0.10.1 and v0.10.1.1

### Does this PR introduce _any_ user-facing change?
branch main of vllm-ascend will not be compatible with vllm v0.10.1 and
v0.10.1.1

### How was this patch tested?
CI passed with existing test.

- vLLM version: v0.10.1.1
- vLLM main:
6fb2788163

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-09-10 08:43:10 +08:00
committed by GitHub
parent 93e28e6862
commit edf1f600ad
22 changed files with 340 additions and 876 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
tests/ut/kv_connector/utils.py
View File

@@ -19,8 +19,6 @@ from vllm.v1.outputs import ModelRunnerOutput
from vllm.v1.request import Request
from vllm.v1.structured_output import StructuredOutputManager
from vllm_ascend.utils import vllm_version_is
EOS_TOKEN_ID = 50256
os.environ["VLLM_USE_V1"] = "1"
@@ -160,27 +158,14 @@ def create_request(
else:
prompt_token_ids = [i * request_id for i in range(num_tokens)]
if vllm_version_is("0.10.1.1") or vllm_version_is("0.10.1"):
req = Request(
request_id=f"id-{request_id}",
prompt_token_ids=prompt_token_ids,
sampling_params=sampling_params,
multi_modal_kwargs=None,
multi_modal_placeholders=None,
multi_modal_hashes=None,
pooling_params=[],
eos_token_id=EOS_TOKEN_ID,
block_hasher=block_hasher,
)
else:
req = Request(
request_id=f"id-{request_id}",
prompt_token_ids=prompt_token_ids,
sampling_params=sampling_params,
pooling_params=[],
eos_token_id=EOS_TOKEN_ID,
block_hasher=block_hasher,
)
req = Request(
request_id=f"id-{request_id}",
prompt_token_ids=prompt_token_ids,
sampling_params=sampling_params,
pooling_params=[],
eos_token_id=EOS_TOKEN_ID,
block_hasher=block_hasher,
)
req.kv_transfer_params = kv_transfer_params
return req
@@ -208,26 +193,15 @@ def create_model_runner_output(
kv_connector_output = KVConnectorOutput(finished_sending=finished_sending,
finished_recving=finished_recving)
extra_args = {"kv_connector_output": kv_connector_output}
if vllm_version_is("0.10.1.1") or vllm_version_is("0.10.1"):
model_runner_output = ModelRunnerOutput(
req_ids=req_ids,
req_id_to_index=req_id_to_index,
sampled_token_ids=sampled_token_ids,
spec_token_ids=None,
logprobs=None,
prompt_logprobs_dict={},
pooler_output=[],
**extra_args,
)
else:
model_runner_output = ModelRunnerOutput(
req_ids=req_ids,
req_id_to_index=req_id_to_index,
sampled_token_ids=sampled_token_ids,
logprobs=None,
prompt_logprobs_dict={},
pooler_output=[],
**extra_args,
)
model_runner_output = ModelRunnerOutput(
req_ids=req_ids,
req_id_to_index=req_id_to_index,
sampled_token_ids=sampled_token_ids,
logprobs=None,
prompt_logprobs_dict={},
pooler_output=[],
**extra_args,
)
return model_runner_output