Skip to content

Pull requests: ggerganov/ggml

New pull request New
Clear current search query, filters, and sorts
30 Open 389 Closed
30 Open 389 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

cuda : fix synchronization with tensor get/set
#659 by slaren was merged Dec 18, 2023 Loading…
fix im2col_f32_f16
#658 by leejet was merged Dec 18, 2023 Loading…
ggml: ggml_conv_2d with winograd convolution implementation + ggml_pad symmetric padding
#654 by FSSRepo was closed Dec 15, 2023 Loading…
2 tasks
3
sync : llama (mul_mat_id + get_rows kernels, typos)
#649 by ggerganov was merged Dec 13, 2023 Loading…
3
Document Mixtral changes to GGUF
#646 by ariez-xyz was merged Dec 13, 2023 Loading…
2
Change installation path of static libraries to standard directory
#645 by davesjoewang was merged Dec 14, 2023 Loading…
ggml : add support for multiple ids rows in ggml_mat_mul_id
#643 by slaren was closed Dec 11, 2023 Loading…
2
ggml-backend : remove backend self-registration
#641 by slaren was merged Dec 7, 2023 Loading…
sync : llama.cpp (fused soft max, gpu cpy ops, etc.)
#640 by ggerganov was merged Dec 7, 2023 Loading…
5
add more int ops
#639 by gwenzek was merged Dec 29, 2023 Loading…
15
test-backend-ops : add performance eval mode + improve CUDA repeat and binary broadcast ops performance
#636 by slaren was merged Dec 7, 2023 Loading…
25
test-backend-ops : initialize ggml_argsort test with unique values
#634 by slaren was merged Dec 5, 2023 Loading…
1
metal : check supported ops at runtime
#632 by ggerganov was merged Dec 5, 2023 Loading…
disable fprintf when building with NDEBUG
#631 by foldl was merged Dec 5, 2023 Loading…
false alarm of error check in ggml_new_tensor_impl()
#629 by foldl was closed Dec 5, 2023 Loading…
5
ggml-cuda : fix usage without CUDA devices
#627 by slaren was merged Dec 1, 2023 Loading…
rocm: Add ROCm's cmake config
#626 by riverzhou was merged Dec 1, 2023 Loading…
ggml : full broadcast in mul, add, div + ggml_mul_mat_id, ggml_argsort, ggml_top_k
#625 by slaren was merged Dec 5, 2023 Loading…
28
ggml: new gpu kernels + extends ggml_leaky_relu + ggml_pad
#621 by FSSRepo was merged Dec 13, 2023 Loading…
10 tasks done
97
ggml-backend update: buffer types, backend registry, graph compare, tests
#620 by slaren was merged Nov 30, 2023 Loading…
9 tasks done
19
Update test-vec0.c
#619 by magicse was merged Nov 23, 2023 Loading…
gguf : add tokenizer.chat_template documentation
#616 by slaren was merged Nov 19, 2023 Loading…
sync : whisper.cpp (update whisper example + minor)
#613 by ggerganov was merged Nov 17, 2023 Loading…
actual inplace set_2d_inplace
#611 by gwenzek was merged Nov 17, 2023 Loading…
1
update examples and tests to use ggml_allocr_new_measure_from_backend
#608 by slaren was merged Nov 13, 2023 Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.