Dev/rebase 0.14.0 (#847)
Signed-off-by: JaredforReal <w13431838023@gmail.com> Signed-off-by: root <root@hk01dgx039.cm.cluster> Signed-off-by: tzhouam <tzhouam@connect.ust.hk> Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk> Signed-off-by: TangPeng <85704592@qq.com> Signed-off-by: XU Mingshi <91017482+mxuax@users.noreply.github.com> Signed-off-by: mxuax <mxuax@connect.ust.hk> Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com> Signed-off-by: zjy0516 <riverclouds.zhu@qq.com> Signed-off-by: iwzbi <wzbi@zju.edu.cn> Signed-off-by: ZeldaHuang <hzm414167@alibaba-inc.com> Signed-off-by: Yuhan Liu <30294295+liuyuhanalex@users.noreply.github.com> Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com> Signed-off-by: samithuang <285365963@qq.com> Signed-off-by: linyueqian <linyueqian@outlook.com> Signed-off-by: David Chen <530634352@qq.com> Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com> Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com> Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com> Signed-off-by: wangyu31577 <wangyu31577@hundsun.com> Signed-off-by: princepride <wangzhipeng628@gmail.com> Signed-off-by: John Liu BUAA <liukecheng97@gmail.com> Signed-off-by: Dinesh G <G.Dinesh@ibm.com> Signed-off-by: gDINESH13 <dinesh13g@gmail.com> Signed-off-by: root <root@hk01dgx028.cm.cluster> Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk> Co-authored-by: JaredforReal <w13431838023@gmail.com> Co-authored-by: root <root@hk01dgx039.cm.cluster> Co-authored-by: JustQJ <37905360+JustQJ@users.noreply.github.com> Co-authored-by: XU Mingshi <91017482+mxuax@users.noreply.github.com> Co-authored-by: Sihyeon Jang <uneedsihyeon@gmail.com> Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com> Co-authored-by: catcat <108673086+iwzbi@users.noreply.github.com> Co-authored-by: Ziming Huang <hzm414167@alibaba-inc.com> Co-authored-by: Yuhan Liu <30294295+liuyuhanalex@users.noreply.github.com> Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com> Co-authored-by: Samit <285365963@qq.com> Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com> Co-authored-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com> Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com> Co-authored-by: wangyu31577 <wangyu31577@hundsun.com> Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com> Co-authored-by: John Liu BUAA <liukecheng97@gmail.com> Co-authored-by: D!NE$H <67671800+gDINESH13@users.noreply.github.com> Co-authored-by: root <root@hk01dgx028.cm.cluster>
This commit is contained in:
64 files changed
+3359
-906
No files matched your search
@@ -8,8 +8,6 @@ from vllm.outputs import PoolingRequestOutput
|
||||
from vllm.sampling_params import RequestOutputKind
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.v1.engine import EngineCoreOutput, EngineCoreRequest, FinishReason
|
||||
from vllm.v1.engine.detokenizer import IncrementalDetokenizer
|
||||
from vllm.v1.engine.logprobs import LogprobsProcessor
|
||||
from vllm.v1.engine.output_processor import OutputProcessor as VLLMOutputProcessor
|
||||
from vllm.v1.engine.output_processor import OutputProcessorOutput, RequestOutputCollector, RequestState
|
||||
from vllm.v1.engine.parallel_sampling import ParentRequest
|
||||
@@ -37,65 +35,6 @@ class OmniRequestState(RequestState):
|
||||
self.mm_type: str | None = None
|
||||
self.mm_accumulated: Dict[str, Any] | None = None
|
||||
|
||||
@classmethod
|
||||
def from_new_request(
|
||||
cls,
|
||||
tokenizer: TokenizerLike,
|
||||
request: EngineCoreRequest,
|
||||
prompt: str | None,
|
||||
parent_req: ParentRequest | None,
|
||||
request_index: int,
|
||||
queue: Any | None,
|
||||
log_stats: bool,
|
||||
stream_interval: int,
|
||||
) -> "OmniRequestState":
|
||||
if sampling_params := request.sampling_params:
|
||||
if not sampling_params.detokenize:
|
||||
tokenizer = None
|
||||
output_kind = sampling_params.output_kind
|
||||
logprobs_processor = LogprobsProcessor.from_new_request(
|
||||
tokenizer=tokenizer,
|
||||
request=request,
|
||||
)
|
||||
detokenizer = IncrementalDetokenizer.from_new_request(
|
||||
tokenizer=tokenizer,
|
||||
request=request,
|
||||
)
|
||||
max_tokens_param = sampling_params.max_tokens
|
||||
top_p = sampling_params.top_p
|
||||
n = sampling_params.n
|
||||
temperature = sampling_params.temperature
|
||||
else:
|
||||
logprobs_processor = None
|
||||
detokenizer = None
|
||||
max_tokens_param = None
|
||||
top_p = None
|
||||
n = None
|
||||
temperature = None
|
||||
assert request.pooling_params is not None
|
||||
output_kind = request.pooling_params.output_kind
|
||||
|
||||
return cls(
|
||||
request_id=request.request_id,
|
||||
parent_req=parent_req,
|
||||
request_index=request_index,
|
||||
lora_name=(request.lora_request.name if request.lora_request is not None else None),
|
||||
output_kind=output_kind,
|
||||
prompt=prompt,
|
||||
prompt_token_ids=request.prompt_token_ids,
|
||||
prompt_embeds=request.prompt_embeds,
|
||||
logprobs_processor=logprobs_processor,
|
||||
detokenizer=detokenizer,
|
||||
max_tokens_param=max_tokens_param,
|
||||
top_p=top_p,
|
||||
n=n,
|
||||
temperature=temperature,
|
||||
arrival_time=request.arrival_time,
|
||||
queue=queue,
|
||||
log_stats=log_stats,
|
||||
stream_interval=stream_interval,
|
||||
)
|
||||
|
||||
def add_multimodal_tensor(self, payload: Any | None, mm_type: str | None) -> None:
|
||||
if payload is None:
|
||||
return
|
||||
|
||||
Reference in new issue
Block a user