Skip to content

ggml : prune - #29801

Draft
ggerganov wants to merge 5 commits into
masterfrom
gg/ggml-prune-deprecated
Draft

ggml : prune#29801
ggerganov wants to merge 5 commits into
masterfrom
gg/ggml-prune-deprecated

Conversation

@ggerganov

@ggerganov ggerganov commented Oct 1, 2026 •
edited
Loading

Copy link
Copy Markdown
Member

Overview

info #30566
rel #30565

Preparing for ggml v1.0.0 release.

Drop deprecated op and functions from ggml.h:

  • GGML_OP_ADD1
  • ggml_mul_mat_set_prec
  • ggml_rope_custom
  • ggml_upscale_ext
  • ggml_flash_attn_ext_set_prec

Also drop the outdated 172-line documentation comment at the top of ggml.h.

TODOs:

Requirements

  • I have read and agree with the contributing guidelines
  • AI usage disclosure: YES
    • Harness: dsh:llama.cpp
    • Hardware: MacBook, M5 Max, 128GB
    • Model: ggml-org/Qwen3.8-Flash-Next-GGUF
    • Stats: ◷ 11.2m · ⚙ 7.7m · ↑ 58k · ↓ 36k · ⇈ 679.3 tok/s · ⇊ 60.2 tok/s · ≡ 146 · ⌨ 17

@ggerganov
ggerganov force-pushed the gg/ggml-prune-deprecated branch from 9a1244a to f13e922 Compare October 1, 2026 11:49
@github-actions github-actions Bot added testing Everything test related Vulkan Issues specific to the Vulkan backend ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language Ascend NPU issues specific to Ascend NPUs CUDA Related to the CUDA backend OpenVINO labels Oct 1, 2026
@0cc4m

0cc4m commented Oct 1, 2026

Copy link
Copy Markdown
Contributor

For vulkan this is missing the actual shader comp file and its generation in vulkan-shaders-gen.cpp

@ggerganov
ggerganov force-pushed the gg/ggml-prune-deprecated branch 2 times, most recently from 0a1a80e to 21ae9cc Compare October 4, 2026 16:41
@ggerganov ggerganov mentioned this pull request Oct 7, 2026
Closed
@ggerganov
ggerganov force-pushed the gg/ggml-prune-deprecated branch from 21ae9cc to b687249 Compare October 13, 2026 18:55
@ggerganov ggerganov mentioned this pull request Oct 15, 2026
Draft
@ggerganov ggerganov changed the title ggml : prune deprecated API ggml : prune Oct 15, 2026
@ggerganov
ggerganov force-pushed the gg/ggml-prune-deprecated branch 2 times, most recently from bb608e4 to 9f8a170 Compare November 8, 2026 11:21
@ggerganov ggerganov mentioned this pull request Nov 8, 2026
Merged
@ggerganov
ggerganov force-pushed the gg/ggml-prune-deprecated branch from 4ae076e to 5da28fd Compare November 9, 2026 10:07
@ggerganov ggerganov mentioned this pull request Nov 9, 2026
Closed
@losewayy losewayy mentioned this pull request Nov 9, 2026
Merged
ggerganov and others added 5 commits November 10, 2026 10:43
@ggerganov
ggml : prune deprecated API
d8ad391
@ggerganov
cont : bump RPC version
d23ea17
@ggerganov
cont : minor
967b99f
@ggerganov
ggml : remove outdated documentation from ggml.h
682c9c9 
The 172-line comment block at the top of the header has not been updated in a
substantive way since the backend v2 split (Nov 2023) and now documents APIs
that no longer exist:

- `ggml_set_f32()`, `ggml_get_f32_1d()`, `ggml_set_f32_1d()` were removed
- `ggml_conv_1d_1s()`, `ggml_conv_1d_2s()` ops no longer exist
- `ggml_set_param()` no longer takes a context argument
- `ggml_graph_compute_with_ctx()` moved to the CPU backend header
- the optimization API now lives in `ggml-opt.h`

The block also ended with 5 empty `TODO` sections.

Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB)
@losewayy @ggerganov
ggml : remove DIAG_MASK_INF and DIAG_MASK_ZERO (#31946)
3650954
@ggerganov
ggerganov force-pushed the gg/ggml-prune-deprecated branch from b18af06 to 3650954 Compare November 10, 2026 08:45
@github-actions github-actions Bot added documentation Improvements or additions to documentation OpenCL Issues specific to the OpenCL backend labels Nov 10, 2026

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@wine99 wine99 Awaiting requested review from wine99 wine99 will be requested when the pull request is marked ready for review wine99 is a code owner
@marty1885 marty1885 Awaiting requested review from marty1885 marty1885 will be requested when the pull request is marked ready for review marty1885 is a code owner
@JohannesGaessler JohannesGaessler Awaiting requested review from JohannesGaessler JohannesGaessler will be requested when the pull request is marked ready for review JohannesGaessler is a code owner

At least 2 approving reviews are required to merge this pull request.

Assignees

No one assigned

Labels

Ascend NPU issues specific to Ascend NPUs CUDA Related to the CUDA backend documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend OpenVINO SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@ggerganov @0cc4m @losewayy