apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 16:22:57 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix typos (#3684)

Browse Source
This commit is contained in:
co63oc
2025-09-01 17:50:17 +08:00
committed by GitHub
parent 0513a78ecc
commit d6369b4d51
67 changed files with 85 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/config.py
View File

@@ -257,7 +257,7 @@ class ParallelConfig:
self.sequence_parallel = False # Whether to enable sequence parallelism.
self.use_ep = False # Whether to enable Expert Parallelism
self.moe_phase = MoEPhase("prefill") # Generation phase
self.msg_queue_id = 1 # mesage queue id
self.msg_queue_id = 1 # message queue id
self.tensor_parallel_rank = 0 # TP rank ID
self.tensor_parallel_size = 1 # TP degree
@@ -549,7 +549,7 @@ class GraphOptimizationConfig:
It requires that all input buffers have fixed addresses, and all
splitting ops write their outputs to input buffers.
- With dyncmic graph backend: ...
- With static grpah backend: WIP
- With static graph backend: WIP
"""
self.sot_warmup_sizes: list[int] = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 16, 32, 64, 128]
""" Number of warmup runs for SOT warmup. """