convert : use f32 outtype for bf16 tensors - #6106
Merged
ggerganov merged 1 commit intoMar 18, 2024
Merged
Conversation
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
Collaborator
ggerganov
approved these changes
Mar 18, 2024
hodlen
pushed a commit
to hodlen/llama.cpp
that referenced
this pull request
Apr 3, 2024
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
phuongncn
pushed a commit
to phuongncn/llama.cpp-gx10-dgx-sparks-deepseekv4
that referenced
this pull request
Apr 28, 2026
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
ljubomirj
pushed a commit
to ljubomirj/llama.cpp
that referenced
this pull request
May 6, 2026
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
my-other-github-account
pushed a commit
to my-other-github-account/llama.cpp
that referenced
this pull request
May 15, 2026
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
AlexiAlp
pushed a commit
to minghaop/llama.cpp
that referenced
this pull request
Jun 2, 2026
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
AlexiAlp
pushed a commit
to minghaop/llama.cpp
that referenced
this pull request
Jun 2, 2026
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
fukuro-kun
pushed a commit
to fukuro-kun/fukuro-llama-cpp-turboquant
that referenced
this pull request
Jul 5, 2026
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
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
3 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.
The old behaviour is to use f16, but bf16 to f16 is not a lossless conversion. Change the outtype to f32 to default to a lossless conversion.
This restores original intended behaviour of #1309.