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

Drop 0.10.2 (#3284)

Browse Source 
Drop v0.10.2 support, we support vLLM 0.11.0rc3 now.
- vLLM version: v0.11.0rc3
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-10-09 10:28:38 +08:00
committed by GitHub
parent 2dde1268c7
commit f12f76d7ba
17 changed files with 202 additions and 653 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
vllm_ascend/sample/sampler.py
View File

@@ -3,13 +3,9 @@ import torch_npu
from vllm.v1.sample.ops.topk_topp_sampler import TopKTopPSampler, random_sample
from vllm.v1.sample.sampler import Sampler
from vllm_ascend.utils import is_310p, vllm_version_is
from vllm_ascend.utils import is_310p
if vllm_version_is("0.10.2"):
from vllm.config import LogprobsMode
DEFAULT_LOGPROBS_MODE = LogprobsMode.RAW_LOGPROBS
else:
DEFAULT_LOGPROBS_MODE = "raw_logprobs"
DEFAULT_LOGPROBS_MODE = "raw_logprobs"
class AscendSampler(Sampler):
@@ -69,18 +65,10 @@ class AscendTopKTopPSampler(TopKTopPSampler):
"""Override pytorch native implementation to torch_npu"""
logits = self._apply_top_k_top_p(logits, k, p)
logits_to_return = None
if vllm_version_is("0.10.2"):
if self.logprobs_mode == LogprobsMode.PROCESSED_LOGITS:
logits_to_return = logits
elif self.logprobs_mode == LogprobsMode.PROCESSED_LOGPROBS:
logits_to_return = logits.log_softmax(dim=-1,
dtype=torch.float32)
else:
if self.logprobs_mode == "processed_logits":
logits_to_return = logits
elif self.logprobs_mode == "processed_logprobs":
logits_to_return = logits.log_softmax(dim=-1,
dtype=torch.float32)
if self.logprobs_mode == "processed_logits":
logits_to_return = logits
elif self.logprobs_mode == "processed_logprobs":
logits_to_return = logits.log_softmax(dim=-1, dtype=torch.float32)
probs = logits.softmax(dim=-1, dtype=torch.float32)
return random_sample(probs, generators), logits_to_return