llama.cpp
ggml: allow casting between f32 and i32
#15783
Merged

ggml: allow casting between f32 and i32 #15783

ngxson
ngxson ggml: allow casting between f32 and i32
f3b489b2
github-actions github-actions added testing
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
github-actions github-actions added Apple Metal
ngxson fix cuda
d4f78de3
ngxson add vulkan
4f57dda5
ngxson fix CPU non-cont
fee65fa1
ngxson add non-cont test case
01af2c2d
github-actions github-actions added Vulkan
ngxson add note
60e8f200
ngxson ngxson marked this pull request as ready for review 98 days ago
ngxson ngxson requested a review from 0cc4m 0cc4m 98 days ago
ngxson ngxson requested a review from CISC CISC 98 days ago
ngxson ngxson requested a review from ggerganov ggerganov 98 days ago
ngxson ngxson requested a review from slaren slaren 98 days ago
slaren
ngxson extend test number range
9f5d5cdf
ngxson correct note
0a2b23c2
ngxson add cont version for vulkan
65b19a00
ngxson
CISC
CISC approved these changes on 2025-09-04
ngxson
CISC
ggerganov
ngxson
0cc4m
0cc4m approved these changes on 2025-09-07
ggerganov
ggerganov approved these changes on 2025-09-07
ngxson ngxson merged 9fcb29f2 into master 95 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone