index
:
ik_llama.cpp.git
main
Unnamed repository; edit this file 'description' to name the repository.
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
examples
/
imatrix
/
imatrix.cpp
Age
Commit message (
Expand
)
Author
2024-04-18
ggml : group all experts in a single ggml_mul_mat_id (#6505)
slaren
2024-04-12
imatrix : remove invalid assert (#6632)
Georgi Gerganov
2024-04-11
eval-callback: Example how to use eval callback for debugging (#6576)
Pierrick Hymbert
2024-04-09
BERT tokenizer fixes (#6498)
Jared Van Bortel
2024-04-03
ggml : mul_mat_id use the same tensor for all the experts (#6387)
slaren
2024-03-26
llama : greatly reduce output buffer memory usage (#6122)
compilade
2024-03-24
imatrix : fix wname for mul_mat_id ops (#6271)
Georgi Gerganov
2024-03-18
backend : offload large batches to GPU (#6083)
slaren
2024-02-16
ggml : add numa options (#5377)
bmwl
2024-02-04
Adding some imatrix tools (#5302)
Kawrakow
2024-01-22
imatrix : keep intermediate imatrix results (#5077)
Kawrakow
2024-01-21
Slightly faster imatrix (#5050)
Kawrakow
2024-01-18
imatrix : fix assert for src0 non-cont check
Georgi Gerganov
2024-01-17
imatrix : offload to GPU support (#4957)
Georgi Gerganov
2024-01-12
Importance Matrix calculation (#4861)
Kawrakow