[V1 Loader] support weight_only (#3413)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled

* support wint4/wint8

* delete smoe case

* update ci

* print log
This commit is contained in:
bukejiyu
2025-08-23 13:13:41 +08:00
committed by GitHub
parent 93e1b63200
commit 77514e3e1e
24 changed files with 1055 additions and 524 deletions

View File

@@ -247,9 +247,9 @@ class Ernie4_5_VLMoeForConditionalGenerationRL(Ernie4_5_VLMoeForConditionalGener
)
if self.fd_config.model_config.moe_use_aux_free:
self.infer_to_train_mapping[
f"{base_name}.{layer_idx}.mlp.{moe_tag}_fused_moe.experts.gate_correction_bias"
] = f"{base_name}.{layer_idx}.mlp.moe_statics.e_score_correction_bias"
self.infer_to_train_mapping[f"{base_name}.{layer_idx}.mlp.gate_correction_bias"] = (
f"{base_name}.{layer_idx}.mlp.moe_statics.e_score_correction_bias"
)
# Initialize defaultdict for expert weights
from collections import defaultdict