-
Notifications
You must be signed in to change notification settings - Fork 966
Issues: ggerganov/ggml
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
ggml : replace conv stage_0 and stage_1 with im2col and mul_mat
refactoring
Refactoring
#559
by ggerganov
was closed Nov 13, 2023
updated Nov 13, 2023
Conv2D kernel CuBLAS implementation - need feedback
#556
by FSSRepo
was closed Nov 13, 2023
updated Nov 13, 2023
[Question] How do I force a computation of a tensor/force a dependency between 2 tensors?
#610
by saharNooby
was closed Nov 14, 2023
updated Nov 14, 2023
Compilation error with make on Linux Lite related to AVX.
#605
by FSSRepo
was closed Nov 11, 2023
updated Nov 15, 2023
gguf : opening an invalid file may cause a out of bounds access
#614
by slaren
was closed Nov 17, 2023
updated Nov 17, 2023
Unable to attach with GDB when hitting GGML_ASSERT after backend v2 changes
bug
Something isn't working
#630
by YavorGIvanov
was closed Dec 4, 2023
updated Dec 4, 2023
[Feature Request] Circular padding tensor operation
#635
by gartia
was closed Dec 6, 2023
updated Dec 6, 2023
What can be used instead ggml_get_backend()?
#656
by bsdero
was closed Dec 16, 2023
updated Dec 16, 2023
make: *** No rule to make target 'gpt-2'. Stop.
#666
by sanliuyi901
was closed Dec 29, 2023
updated Dec 29, 2023
test-conv1d and test-conv2d failed on GPUs with computation capability <= 6.1
#668
by bssrdf
was closed Dec 29, 2023
updated Dec 29, 2023
ggml : add option for controlling work distribution across threads
performance
Speed related topics
refactoring
Refactoring
#291
by ggerganov
was closed Jan 5, 2024
updated Jan 5, 2024
ggml_allocr_alloc_graph allocated overlapping tensor memory
#700
by bssrdf
was closed Jan 18, 2024
updated Jan 18, 2024
Any tutorial to convert pytroch model to gguf?
#705
by BayRanger
was closed Jan 29, 2024
updated Jan 29, 2024
Matmul on 4d tensors with cuda backend
#672
by balisujohn
was closed Jan 29, 2024
updated Jan 29, 2024
some notes about how ggml works using the GPT-2 example
#711
by chunhualiao
was closed Jan 29, 2024
updated Jan 29, 2024
"array size is too large" on model load
#714
by iamlemec
was closed Jan 29, 2024
updated Jan 29, 2024
why add 512 : ggml_backend_alloc_buffer(backend_kv, memory_size + 512*2);
#637
by EveningLin
was closed Jan 29, 2024
updated Jan 29, 2024
ggml : improve memory allocation for weights and similar lists of tensors
refactoring
Refactoring
#578
by slaren
was closed Jan 30, 2024
updated Jan 30, 2024
ggml : simplify the ggml_compute_forward_ calls
good first issue
Good for newcomers
refactoring
Refactoring
#724
by ggerganov
was closed Feb 21, 2024
updated Feb 21, 2024
ggml : make ggml_fp16_t private
refactoring
Refactoring
#720
by ggerganov
was closed Feb 22, 2024
updated Feb 22, 2024
ProTip!
Adding no:label will show everything without a label.