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

sync : llama.cpp (ggml-backend)
#696 by ggerganov was merged Jan 12, 2024 Loading…
2
metal : add debug capture backend function
#694 by jmousseau was merged Jan 29, 2024 Loading…
2
remove ggml_cpy_inplace and ggml_cont_inplace, close ggerganov#622
#693 by 4imothy was merged Jan 11, 2024 Loading…
1
Update README.md
#692 by otaGran was merged Jan 10, 2024 Loading…
1
1
ggml: add ggml_is_4d()
#691 by ide-rea was closed Jan 20, 2024 Loading…
1
metal : wrap each operation in debug group
#690 by jmousseau was merged Jan 10, 2024 Loading…
5
Fix execlp call
#689 by Halalaluyafail3 was merged Jan 9, 2024 Loading…
feat: use direct type casting instead of memcpy
#688 by miaoerduo was closed Jan 9, 2024 • Draft
3
feat: use direct type casting instead of memcpy
#687 by miaoerduo was closed Jan 9, 2024 • Draft
ggml_cuda_cpy support for 4d tensors and float16->float32 upcasting
#686 by balisujohn was merged Jan 29, 2024 Loading…
11
added cuda float16->float32 upcasting to ggml_cuda_cpy
#685 by balisujohn was closed Jan 12, 2024 Loading…
2
fix ROCm on Windows
#683 by Cyberhan123 was merged Jan 6, 2024 Loading…
12
change GGML_MAX_NAME to 128
#682 by leejet was merged Jan 10, 2024 Loading…
9
metal : switch back to default.metallib
#681 by ggerganov was merged Jan 5, 2024 Loading…
fix : cuda order of synchronization when setting a buffer
#679 by Green-Sky was merged Jan 5, 2024 Loading…
2
scripts : allow to skip commits during sync
#678 by ggerganov was merged Jan 3, 2024 Loading…
sync : llama.cpp
#677 by ggerganov was merged Jan 3, 2024 Loading…
2
Add keys for kv sizes to GGUF spec
#676 by postmasters was merged Jan 5, 2024 Loading…
Adds Swift Package declaration for GGML
#674 by 1-ashraful-islam was merged Jan 3, 2024 Loading…
Update README.md
#671 by astariul was merged Dec 29, 2023 Loading…
1
Fix mul-mat error for older GPUs
#669 by bssrdf was merged Dec 29, 2023 Loading…
2
15
scripts : add sync-whisper-am.sh
#667 by ggerganov was merged Dec 29, 2023 Loading…
sync : llama.cpp
#665 by ggerganov was merged Dec 27, 2023 Loading…
4
Add steps for Android compilation and inference.
#664 by mynkpl1998 was merged Dec 29, 2023 Loading…
sync : llama.cpp (ggml_scale, ggml_row_size, ggml_mul_mat_set_prec)
#662 by ggerganov was merged Dec 22, 2023 Loading…
1
ProTip! Follow long discussions with comments:>50.