Skip to content

fix: improve quantization and runtime correctness - #3054

Closed
ZX-ModelCloud wants to merge 1 commit into
mainfrom
fix/quantization-runtime-correctness
Closed

fix: improve quantization and runtime correctness#3054
ZX-ModelCloud wants to merge 1 commit into
mainfrom
fix/quantization-runtime-correctness

Conversation

@ZX-ModelCloud

Copy link
Copy Markdown
Collaborator

Summary:

  • Release Hessian partials.
  • Safe sharded-load capability defaults.
  • Instance loader/lm_head.
  • ERNIE projection paths.
  • GiB formatting.

Tests:

  • Targeted: 92 passed, 35 skipped.
  • Module-tree: 106 passed, 2 deselected.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant