apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Modified to support custom all reduce by default (#3538)

Browse Source
This commit is contained in:
zhink
2025-08-22 16:59:05 +08:00
committed by GitHub
parent 27666ee586
commit df7c31012b
15 changed files with 18 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/config.py
View File

@@ -278,7 +278,7 @@ class ParallelConfig:
self.disable_any_whitespace: bool = True
self.pod_ip: str = None
# enable the custom all-reduce kernel and fall back to NCCL(dist.all_reduce).
self.enable_custom_all_reduce: bool = False
self.disable_custom_all_reduce: bool = False
for key, value in args.items():
if hasattr(self, key):
setattr(self, key, value)

12
fastdeploy/engine/args_utils.py
View File

@@ -188,7 +188,7 @@ class EngineArgs:
Flag to enable prefix caching.
"""
enable_custom_all_reduce: bool = False
disable_custom_all_reduce: bool = False
"""
Flag to enable the custom all-reduce kernel.
"""
@@ -571,10 +571,10 @@ class EngineArgs:
help="Degree of tensor parallelism.",
)
parallel_group.add_argument(
"--enable-custom-all-reduce",
"--disable-custom-all-reduce",
action="store_true",
default=EngineArgs.enable_custom_all_reduce,
help="Flag to enable custom all-reduce.",
default=EngineArgs.disable_custom_all_reduce,
help="Flag to disable custom all-reduce.",
)
parallel_group.add_argument(
"--max-num-seqs",
@@ -947,10 +947,6 @@ class EngineArgs:
early_stop_cfg = self.create_early_stop_config()
early_stop_cfg.update_enable_early_stop(self.enable_early_stop)
assert not (
self.tensor_parallel_size <= 1 and self.enable_custom_all_reduce
), "enable_custom_all_reduce must be used with tensor_parallel_size>1"
assert is_port_available(
"0.0.0.0", self.engine_worker_queue_port
), f"The parameter `engine_worker_queue_port`:{self.engine_worker_queue_port} is already in use."

2
fastdeploy/engine/engine.py
View File

@@ -1118,7 +1118,7 @@ class LLMEngine:
"do_profile": self.do_profile,
"dynamic_load_weight": self.cfg.load_config.dynamic_load_weight,
"disable_any_whitespace": self.cfg.disable_any_whitespace,
"enable_custom_all_reduce": self.cfg.parallel_config.enable_custom_all_reduce,
"disable_custom_all_reduce": self.cfg.parallel_config.disable_custom_all_reduce,
"enable_logprob": self.cfg.model_config.enable_logprob,
}
for worker_flag, value in worker_append_flag.items():

2
fastdeploy/worker/gpu_worker.py
View File

@@ -69,7 +69,7 @@ class GpuWorker(WorkerBase):
gc.collect()
paddle.device.cuda.empty_cache()
if (
self.parallel_config.enable_custom_all_reduce
not self.parallel_config.disable_custom_all_reduce
and self.parallel_config.tensor_parallel_size > 1
and paddle.is_compiled_with_cuda()
):

2
fastdeploy/worker/worker_process.py
View File

@@ -516,7 +516,7 @@ def parse_args():
help="enable prefix cache",
)
parser.add_argument(
"--enable_custom_all_reduce",
"--disable_custom_all_reduce",
action="store_true",
help="enable custom all-reduce",
)