-
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
New CUDA changes completely break rwkv.cpp
#272
by LoganDark
was closed Jun 20, 2023
updated Jun 20, 2023
ggml : add NUMA support
enhancement
New feature or request
performance
Speed related topics
#290
by ggerganov
was closed Jun 26, 2023
updated Jun 26, 2023
ggml_new_tensor_impl: not enough space in the context's memory pool
#322
by daulet
was closed Jun 30, 2023
updated Jun 30, 2023
Concerns about ggml_graph_compute's threading
#324
by CCLDArjun
was closed Jun 30, 2023
updated Jun 30, 2023
ggml : new operations supported in New feature or request
encodec.cpp
enhancement
#281
by PABannier
was closed Jul 2, 2023
updated Jul 2, 2023
ggml_bert_new_tensor_impl: not enough space in the context's memory pool
#327
by luoweb
was closed Jul 2, 2023
updated Jul 2, 2023
Profiling oddity - why so slow sometimes?
#183
by evanmiller
was closed Jul 4, 2023
updated Jul 4, 2023
ggml : generalize Good for newcomers
refactoring
Refactoring
quantize_fns
for simpler FP16 handling
good first issue
#286
by ggerganov
was closed Jul 5, 2023
updated Jul 5, 2023
ggml : Good for newcomers
refactoring
Refactoring
ggml_graph_compute
should not require ggml_context
good first issue
#287
by ggerganov
was closed Jul 7, 2023
updated Jul 7, 2023
Considering ggml 2D tensors are row major, the comment in ggml.h at line 136 and 138 looks incorrect
#348
by sankalpdayal
was closed Jul 10, 2023
updated Jul 10, 2023
ggml : remove Good for newcomers
refactoring
Refactoring
src0
and src1
from ggml_tensor
and rename opt
to src
good first issue
#341
by ggerganov
was closed Jul 11, 2023
updated Jul 11, 2023
Possibly missing type conversions in ggml_set_i32 and ggml_set_f32
bug
Something isn't working
#329
by goerch
was closed Jul 11, 2023
updated Jul 11, 2023
A quick question: how do I calculate overhead for a model?
#356
by znsoftm
was closed Jul 11, 2023
updated Jul 11, 2023
add /cmp-nct/ggllm.cpp as falcon example in readme.md
#361
by maddes8cht
was closed Jul 11, 2023
updated Jul 11, 2023
ggml : add mechanism to abort New feature or request
good first issue
Good for newcomers
ggml_graph_compute()
enhancement
#308
by ggerganov
was closed Jul 11, 2023
updated Jul 11, 2023
Can anyone give us a little of materials about qunatization algorith, such as the different between q4_0 and q4_1?
#366
by znsoftm
was closed Jul 11, 2023
updated Jul 11, 2023
ProTip!
Follow long discussions with comments:>50.