Skip to content

Pull requests: ggerganov/ggml

New pull request New
Clear current search query, filters, and sorts
32 Open 398 Closed
32 Open 398 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

Add metal kernel to target resources when built as shared library
#403 by abetlen was merged Jul 23, 2023 Loading…
2 👍 2
ggml : add ggml_map_custom1-3
#422 by slaren was merged Aug 1, 2023 Loading…
1
3 👍 2
Removed duplicate lines in convert-pt-to-ggml.py whisper example
#256 by avilum was merged Jun 18, 2023 Loading…
👍 2
zig : add tests codes using zig
#315 by codingonion was merged Jul 2, 2023 Loading…
👍 2
ggml-backend : metal
#552 by ggerganov was merged Oct 6, 2023 Loading…
3 👍 2
sync : llama.cpp
#764 by ggerganov was merged Mar 14, 2024 Loading…
1 👍 2
ggml : make src0 broadcast-able into src1 for ggml_mul_mat()
#224 by ggerganov was closed Jul 12, 2023 • Draft
1
1 👍 2
Fix examples tensor name access
#443 by klosax was merged Aug 16, 2023 Loading…
1 👍 2
ggml backends interface v1
#547 by slaren was merged Oct 6, 2023 Loading…
34 👍 2
add some new ops, fix some operators and add batch operations to certain operators.
#747 by leejet was merged Mar 3, 2024 Loading…
37 👍 2
gguf : add Mamba keys and tensors
#763 by compilade was merged Mar 13, 2024 Loading…
👍 2
Batch inference
#325 by monatis was merged Jul 12, 2023 Loading…
@ggerganov
13 👍 2
Add parallel decoding in GPT2 example
#572 by YavorGIvanov was merged Oct 12, 2023 Loading…
3 👍 2
Conv 2D CPU Implementation
#352 by dmille was merged Jul 14, 2023 Loading…
4 👍 2
add falcon7b example
#231 by apage43 was closed Oct 16, 2023 Loading…
63 👍 2
ggml: Backport ggml-alloc from llama.cpp
#433 by smspillaz was merged Aug 16, 2023 Loading…
2 👍 2
Support for convolution row sizes undivisible by 32 in ggml_conv_2d_sk_p0
#274 by monatis was merged Jun 25, 2023 Loading…
6 👍 2
ggml: new gpu kernels + extends ggml_leaky_relu + ggml_pad
#621 by FSSRepo was merged Dec 13, 2023 Loading…
10 tasks done
97 👍 2
Add bert.cpp to README
#114 by skeskinen was merged Apr 28, 2023 Loading…
👍 2
SAM: Remove ggml_repeat and use inplace operations
#493 by YavorGIvanov was merged Sep 5, 2023 Loading…
👍 1
Add MNIST example with CNN
#485 by rgerganov was merged Aug 28, 2023 Loading…
6 👍 1
Start using ggml-alloc in SAM example
#490 by YavorGIvanov was merged Aug 28, 2023 Loading…
2 👍 1
make ggml_conv_2d faster
#483 by leejet was merged Oct 9, 2023 Loading…
@ggerganov
16 👍 1
ggml : fix ggml_nbytes with views, add bounds checks to views
#491 by slaren was closed Aug 30, 2023 • Draft
5 👍 1
ggml : sync llama.cpp (gguf + metal + ROCm + etc.)
#489 by ggerganov was merged Aug 28, 2023 Loading…
👍 1
ProTip! no:milestone will show everything without a milestone.