Skip to content

support/fix more IQ OPs #6521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
NeoZhangJianyu merged 1 commit into from
Apr 7, 2024
Merged

support/fix more IQ OPs #6521

NeoZhangJianyu merged 1 commit into from
Apr 7, 2024

Conversation

@NeoZhangJianyu
Copy link
Collaborator

@NeoZhangJianyu NeoZhangJianyu commented Apr 7, 2024

  1. support/fix the more OPs:
  • GGML_TYPE_IQ4_NL
  • GGML_TYPE_IQ4_XS
  • GGML_TYPE_IQ3_XXS
  • GGML_TYPE_IQ3_S
  • GGML_TYPE_IQ2_XXS
  • GGML_TYPE_IQ2_XS
  • GGML_TYPE_IQ2_S
  • GGML_TYPE_IQ1_S
  • GGML_TYPE_IQ1_M.
  1. fix the all fault Unit-test cases.
    except:
    • all MUL_MAT_ID cases, due to the interface is changed.
    • MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1]): [MUL_MAT] NMSE = 0.292746658 > 0.000500000 FAIL
      above fault cases will be fixed later.

@NeoZhangJianyu
support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS…
f381347 
…, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M
@NeoZhangJianyu NeoZhangJianyu requested a review from airMeng April 7, 2024 02:18
@airMeng airMeng mentioned this pull request Apr 7, 2024
Closed
@NeoZhangJianyu NeoZhangJianyu merged commit d4f220a into ggml-org:master Apr 7, 2024
This was referenced Apr 7, 2024
Closed
Closed
Closed
Closed
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

1 more reviewer

@airMeng airMeng airMeng approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@NeoZhangJianyu @airMeng