Skip to content

fix pause reqs #741

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 20, 2025
Merged

fix pause reqs #741

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e4e222f
fix pause reqs
Feb 20, 2025
b34ad11
fix
hiworldwzj Feb 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions lightllm/server/router/manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,7 @@ async def _step(self):
paused_reqs = select_paused_reqs(
self.running_batch, self.pause_strategy, self.req_queue, self.max_total_token_num
)
await self._pause_reqs(self.running_batch, paused_reqs)
await self._pause_reqs(paused_reqs)
logger.debug(f"pasued req num: {self.req_queue.get_paused_req_num()}")
self.has_wait_tokens = 0
return
Expand Down Expand Up @@ -342,9 +342,9 @@ async def _decode_batch(self, batch: Batch):
)
return

async def _pause_reqs(self, batch: Batch, pasue_reqs):
async def _pause_reqs(self, pasue_reqs):
pasue_req_ids = [r.request_id for r in pasue_reqs]
await self.model_rpc_client.pause_reqs(batch.batch_id, pasue_req_ids)
await self.model_rpc_client.pause_reqs(pasue_req_ids)
return

def _filter_runing_batch(self):
Expand Down
2 changes: 2 additions & 0 deletions lightllm/server/router/model_infer/mode_backend/chunked_prefill/impl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,8 @@ def post_handel(self, run_reqs: List[InferReq], next_token_ids, next_token_logpr

req_obj.cur_kv_len = len(req_obj.get_chuncked_input_token_ids())
if req_obj.cur_kv_len < req_obj.get_cur_total_len():
if self.tp_rank < self.dp_size:
req_obj.shm_req.shm_cur_kv_len = req_obj.cur_kv_len
continue

req_obj.set_next_gen_token_id(next_token_id, next_token_logprob)
Expand Down