transformers
Fix Glm4MoeIntegrationTest: device_map=auto + MemoryCleanupMixin
#48806
Closed
Closed
Fix Glm4MoeIntegrationTest: device_map=auto + MemoryCleanupMixin #48806
ydshieh
wants to merge
4 commits into
main
from
fix-glm4-moe-integration-test
Fix Glm4MoeIntegrationTest: device_map=auto, bfloat16, MemoryCleanupM…
82cd4e0a
Switch to 4-bit quantization: bfloat16 (716 GiB) OOMs both runners
45e742d9
Fix Glm4MoeIntegrationTest: offload_folder + remove 4bit quantization
4bcf0cc1
Comment out generate calls in Glm4MoeIntegrationTest, keep only loading
29b77cb9
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub