CUDA: Do not mutate cgraph for fused ADDs#19566
Merged
am17an merged 3 commits intoggml-org:masterfrom Feb 13, 2026
Merged
Conversation
1. We should try to minimize in-place changes to the incoming ggml_cgraph where possible (those should happen in graph_optimize) 2. Modifying in-place leads to an additional, unnecessary graph capture step as we store the properties before modifying the graph in-place in the cuda-backend
am17an
reviewed
Feb 12, 2026
am17an
approved these changes
Feb 12, 2026
am17an
reviewed
Feb 12, 2026
Co-authored-by: Aman Gupta <amangupta052@gmail.com>
3 tasks
ronaldmannak
pushed a commit
to PicoMLX/llama.cpp
that referenced
this pull request
Feb 16, 2026
* Do not mutate cgraph for fused ADDs 1. We should try to minimize in-place changes to the incoming ggml_cgraph where possible (those should happen in graph_optimize) 2. Modifying in-place leads to an additional, unnecessary graph capture step as we store the properties before modifying the graph in-place in the cuda-backend * Assert ggml_tensor is trivially copyable * Update ggml/src/ggml-cuda/ggml-cuda.cu Co-authored-by: Aman Gupta <amangupta052@gmail.com> --------- Co-authored-by: Aman Gupta <amangupta052@gmail.com> (cherry picked from commit 43919b7)
liparetejas
pushed a commit
to liparetejas/llama.cpp
that referenced
this pull request
Feb 23, 2026
* Do not mutate cgraph for fused ADDs 1. We should try to minimize in-place changes to the incoming ggml_cgraph where possible (those should happen in graph_optimize) 2. Modifying in-place leads to an additional, unnecessary graph capture step as we store the properties before modifying the graph in-place in the cuda-backend * Assert ggml_tensor is trivially copyable * Update ggml/src/ggml-cuda/ggml-cuda.cu Co-authored-by: Aman Gupta <amangupta052@gmail.com> --------- Co-authored-by: Aman Gupta <amangupta052@gmail.com>
bartowski1182
pushed a commit
to bartowski1182/llama.cpp
that referenced
this pull request
Mar 2, 2026
* Do not mutate cgraph for fused ADDs 1. We should try to minimize in-place changes to the incoming ggml_cgraph where possible (those should happen in graph_optimize) 2. Modifying in-place leads to an additional, unnecessary graph capture step as we store the properties before modifying the graph in-place in the cuda-backend * Assert ggml_tensor is trivially copyable * Update ggml/src/ggml-cuda/ggml-cuda.cu Co-authored-by: Aman Gupta <amangupta052@gmail.com> --------- Co-authored-by: Aman Gupta <amangupta052@gmail.com>
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
Mar 3, 2026
* Do not mutate cgraph for fused ADDs 1. We should try to minimize in-place changes to the incoming ggml_cgraph where possible (those should happen in graph_optimize) 2. Modifying in-place leads to an additional, unnecessary graph capture step as we store the properties before modifying the graph in-place in the cuda-backend * Assert ggml_tensor is trivially copyable * Update ggml/src/ggml-cuda/ggml-cuda.cu Co-authored-by: Aman Gupta <amangupta052@gmail.com> --------- Co-authored-by: Aman Gupta <amangupta052@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
graph_optimizefunction)ggml_cuda_graph_node_set_propertiesviaggml_cuda_graph_update_requiredbefore enteringggml_cuda_graph_evaluate_and_capture.Isolated from #19521