apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Feature] use phi permute/unpermute & rm swiglu (#6361)

Browse Source 
* tp文字输出正常

* B eb5 mini文字输出正常

* eb5mini ep B卡 文字输出正常

* default use phi moe op

* stash

* tp H卡正常

* ep ok

* rm debug

* rm debug tool

* rm del ffn_out

* rm swiglu

* add envs to swiglu

* merge dev

* fix ci baseline

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix ci baseline 2

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
fxyfxy777
2026-03-12 17:01:57 +08:00
committed by GitHub
parent a3d7979711
commit 250ce40b40
18 changed files with 187 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/e2e/utils/rollout_routing_replay_test_utils.py
+2 -2
View File
@@ -157,10 +157,10 @@ def check_routing_replay_chat_completion(openai_client, moe_layer_num: int, mode
model_path = os.getenv("MODEL_PATH")
if model_path:
baseline_path = os.path.join(
model_path, f"R3_BaseLine_dev_uint8_0205/routing_replay_output_baseline_{model_name}"
model_path, f"R3_BaseLine_dev_uint8_0311/routing_replay_output_baseline_{model_name}"
)
else:
baseline_path = f"./R3_BaseLine_dev_uint8_0205/routing_replay_output_baseline_{model_name}"
baseline_path = f"./R3_BaseLine_dev_uint8_0311/routing_replay_output_baseline_{model_name}"
stream_baseline_path = os.path.join(baseline_path, "r3_chat_completion_stream")
nonstream_baseline_path = os.path.join(baseline_path, "r3_chat_completion_nonstream")