[Rebase] Rebase to vllm v0.21.0 (#3530)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk> Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk> Signed-off-by: NumberWan <wantszkin2003@gmail.com> Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com> Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com> Signed-off-by: Dnoob <dxpouo@gmail.com> Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com> Signed-off-by: rein yang <ruiruyang2@gmail.com> Signed-off-by: Nick Cao <ncao@redhat.com> Signed-off-by: zhumingjue <zhumingjue@huawei.com> Signed-off-by: Ricardo Noriega De Soto <rnoriega@redhat.com> Signed-off-by: lyj-jjj <liuyingjun5@huawei.com> Signed-off-by: gcanlin <canlinguosdu@gmail.com> Signed-off-by: wangyu <410167048@qq.com> Signed-off-by: weizhoublue <weizhoublue@github.com> Signed-off-by: weizhou.lan@daocloud.io <weizhou.lan@daocloud.io> Signed-off-by: dengyunyang <584797741@qq.com> Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com> Signed-off-by: David Chen <530634352@qq.com> Signed-off-by: Jie Liu <33612777+keeper-jie@users.noreply.github.com> Signed-off-by: Yueqian Lin <linyueqian@outlook.com> Signed-off-by: princepride <wangzhipeng628@gmail.com> Signed-off-by: natureofnature <wzliu@connect.hku.hk> Signed-off-by: bjf-frz <frz123db@gmail.com> Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com> Signed-off-by: KexiongYu <yukexiong1@huawei.com> Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com> Signed-off-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com> Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com> Co-authored-by: NumberWan <wantszkin2003@gmail.com> Co-authored-by: dsinghvi <divyanshsinghvi@gmail.com> Co-authored-by: Dnoob <dxpouo@gmail.com> Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com> Co-authored-by: Samit <285365963@qq.com> Co-authored-by: rein yang <73573651+R2-Y@users.noreply.github.com> Co-authored-by: Nick Cao <ncao@redhat.com> Co-authored-by: zhumingjue138 <zhumingjue@huawei.com> Co-authored-by: Ricardo Noriega <rnoriega@redhat.com> Co-authored-by: lyj-jjj <liuyingjun5@huawei.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: gcanlin <canlinguosdu@gmail.com> Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com> Co-authored-by: weizhoublue <45163302+weizhoublue@users.noreply.github.com> Co-authored-by: weizhoublue <weizhoublue@github.com> Co-authored-by: dengyunyang <584797741@qq.com> Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com> Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com> Co-authored-by: Jie Liu <33612777+keeper-jie@users.noreply.github.com> Co-authored-by: Yueqian Lin <linyueqian@outlook.com> Co-authored-by: NATURE <wzliu@connect.hku.hk> Co-authored-by: bjf-frz <frz123db@gmail.com> Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com> Co-authored-by: Y. Fisher <yukexiong1@huawei.com> Co-authored-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
+20









Zhou Taichang
Claude Opus 4.7
NumberWan
dsinghvi
Dnoob
Yueqian Lin
Hongsheng Liu
knlnguyen1802
Samit
rein yang
Nick Cao
zhumingjue138
Ricardo Noriega
lyj-jjj
Cursor
gcanlin
wangyu
weizhoublue
weizhoublue
dengyunyang
汪志鹏
WeiQing Chen
Jie Liu
Yueqian Lin
NATURE
bjf-frz
amy-why-3459
Y. Fisher
Zeyu Huang | 黃澤宇
Copilot Autofix powered by AI authored and
GitHub committed 2026-05-16 18:18:43 +08:00
1 parent
5e1986206f
commit
eb4e60ee64
46 files changed
+589
-258
No files matched your search
@@ -203,6 +203,14 @@ class OmniARScheduler(OmniSchedulerMixin, VLLMScheduler):
|
||||
return False
|
||||
|
||||
def schedule(self) -> SchedulerOutput: # type: ignore[override]
|
||||
# Remove FINISHED_ABORTED requests before the upstream scheduler sees
|
||||
# them. Upstream vllm raises RuntimeError on this status; omni allows
|
||||
# async abort (e.g. client disconnect during TTS streaming) to leave
|
||||
# requests in the waiting/running queues temporarily.
|
||||
for queue in (self.waiting, self.running):
|
||||
for req in list(queue):
|
||||
if getattr(req, "status", None) == RequestStatus.FINISHED_ABORTED:
|
||||
queue.remove(req)
|
||||
connector_output = self._latest_omni_connector_output
|
||||
self._latest_omni_connector_output = None
|
||||
if self.input_coordinator:
|
||||
@@ -250,6 +258,7 @@ class OmniARScheduler(OmniSchedulerMixin, VLLMScheduler):
|
||||
lora_request=nr.lora_request,
|
||||
# Enrich with omni payloads from the live request object
|
||||
prompt_embeds=(getattr(request, "prompt_embeds", None) if request else None),
|
||||
prompt_is_token_ids=nr.prompt_is_token_ids,
|
||||
additional_information=(getattr(request, "additional_information", None) if request else None),
|
||||
)
|
||||
new_list.append(omni_nr)
|
||||
@@ -419,7 +428,11 @@ class OmniARScheduler(OmniSchedulerMixin, VLLMScheduler):
|
||||
stopped = True
|
||||
|
||||
if stopped:
|
||||
routed_experts = self._get_routed_experts(request)
|
||||
if (
|
||||
model_runner_output.routed_experts_dict is not None
|
||||
and req_id in model_runner_output.routed_experts_dict
|
||||
):
|
||||
routed_experts = model_runner_output.routed_experts_dict[req_id]
|
||||
|
||||
# Capture finish_reason BEFORE _handle_stopped_request, which may
|
||||
# reset the status to WAITING for streaming requests that continue.
|
||||
|
||||
@@ -337,6 +337,7 @@ class OmniGenerationScheduler(OmniSchedulerMixin, VLLMScheduler):
|
||||
lora_request=nr.lora_request,
|
||||
# Enrich with omni payloads from the live request object
|
||||
prompt_embeds=(getattr(request, "prompt_embeds", None) if request else None),
|
||||
prompt_is_token_ids=nr.prompt_is_token_ids,
|
||||
additional_information=(getattr(request, "additional_information", None) if request else None),
|
||||
)
|
||||
new_list.append(omni_nr)
|
||||
@@ -520,7 +521,11 @@ class OmniGenerationScheduler(OmniSchedulerMixin, VLLMScheduler):
|
||||
stopped = True
|
||||
|
||||
if stopped:
|
||||
routed_experts = self._get_routed_experts(request)
|
||||
if (
|
||||
model_runner_output.routed_experts_dict is not None
|
||||
and req_id in model_runner_output.routed_experts_dict
|
||||
):
|
||||
routed_experts = model_runner_output.routed_experts_dict[req_id]
|
||||
finish_reason = request.get_finished_reason()
|
||||
finished = self._handle_stopped_request(request)
|
||||
if finished:
|
||||
|
||||
@@ -54,6 +54,7 @@ class OmniNewRequestData(NewRequestData):
|
||||
num_computed_tokens=request.num_computed_tokens,
|
||||
lora_request=request.lora_request,
|
||||
prompt_embeds=getattr(request, "prompt_embeds", None),
|
||||
prompt_is_token_ids=getattr(request, "prompt_is_token_ids", None),
|
||||
prefill_token_ids=prefill_token_ids,
|
||||
additional_information=getattr(request, "additional_information", None),
|
||||
)
|
||||
|
||||
Reference in new issue
Block a user