Skip to content

ggml : extend bin bcast for permuted src1#19484

Merged
ggerganov merged 4 commits intomasterfrom
gg/bin-bcast-extend
Feb 11, 2026
Merged

ggml : extend bin bcast for permuted src1#19484
ggerganov merged 4 commits intomasterfrom
gg/bin-bcast-extend

Conversation

@ggerganov
Copy link
Member

@ggerganov ggerganov commented Feb 10, 2026

  • Remove CPU asserts preventing src1 from being permuted
  • Update CUDA kernels to support permuted src1
  • Add tests to exercise src1 permutation

@github-actions github-actions bot added testing Everything test related Nvidia GPU Issues specific to Nvidia GPUs ggml changes relating to the ggml tensor library for machine learning labels Feb 10, 2026
@ggerganov ggerganov marked this pull request as ready for review February 10, 2026 15:13
@ggerganov ggerganov requested a review from am17an February 10, 2026 15:14
@ggerganov ggerganov merged commit 89181c0 into master Feb 11, 2026
71 of 78 checks passed
@ggerganov ggerganov deleted the gg/bin-bcast-extend branch February 11, 2026 05:52
liparetejas pushed a commit to liparetejas/llama.cpp that referenced this pull request Feb 23, 2026
* tests : extend bin bcast for permuted src1

* cont : extend bin support

* cont : s0 is always 1

* tests : simplify
bartowski1182 pushed a commit to bartowski1182/llama.cpp that referenced this pull request Mar 2, 2026
* tests : extend bin bcast for permuted src1

* cont : extend bin support

* cont : s0 is always 1

* tests : simplify
ArberSephirotheca pushed a commit to ArberSephirotheca/llama.cpp that referenced this pull request Mar 3, 2026
* tests : extend bin bcast for permuted src1

* cont : extend bin support

* cont : s0 is always 1

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

Labels

ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants