apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Support mixed deployment with yiyan adapter in develop (#3976)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* [Feature] Support mixed deployment with yiyan adapter in release2.2

* fix metrics

* add unit test

* add unit test

* add unit test

* fix ci

* fix for eb5

* fix ci

* fix ci

* fix ci

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
chenjian
2025-09-18 01:52:20 +08:00
committed by GitHub
parent 2745f37017
commit 618ccdbfba
14 changed files with 934 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
fastdeploy/output/token_processor.py
View File

@@ -29,7 +29,7 @@ import zmq
from fastdeploy import envs
from fastdeploy.engine.request import CompletionOutput, RequestMetrics, RequestOutput
from fastdeploy.inter_communicator import IPCSignal, ZmqClient
from fastdeploy.inter_communicator import IPCSignal, ZmqIpcServer
from fastdeploy.metrics.metrics import main_process_metrics
from fastdeploy.platforms import current_platform
from fastdeploy.utils import llm_logger, spec_logger
@@ -58,12 +58,11 @@ class TokenProcessor:
self.split_connector = split_connector
if envs.FD_USE_GET_SAVE_OUTPUT_V1:
llm_logger.debug(f"create zmq get_save_output_rank{self.cfg.parallel_config.local_data_parallel_id}")
self.zmq_server = ZmqClient(
self.zmq_server = ZmqIpcServer(
name=f"get_save_output_rank{self.cfg.parallel_config.local_data_parallel_id}", mode=zmq.PULL
)
self.zmq_server.start_server()
self.zmq_server.create_router()
self.speculative_decoding = self.cfg.speculative_config.method is not None
self.use_logprobs = self.cfg.model_config.enable_logprob
@@ -498,6 +497,7 @@ class TokenProcessor:
metrics = RequestMetrics(
arrival_time=task.arrival_time,
inference_start_time=task.inference_start_time,
model_execute_time=time.time() - task.inference_start_time,
first_token_time=time.time() - task.inference_start_time,
time_in_queue=task.schedule_start_time - task.preprocess_end_time,
preprocess_cost_time=task.preprocess_end_time - task.preprocess_start_time,
@@ -510,6 +510,7 @@ class TokenProcessor:
metrics = RequestMetrics(
arrival_time=time.time(),
request_start_time=task.arrival_time,
model_execute_time=time.time() - task.inference_start_time,
)
self.number_of_output_tokens += len(token_ids)
self._record_metrics(task, current_time, token_ids)