 Diego Devesa
|
bcbddcd54f
tests : fix test-opt with GGML_BACKEND_DL (#15599)
|
hai 4 meses |
 Johannes Gäßler
|
e92734d51b
test-opt: allow slight inprecision (#15503)
|
hai 4 meses |
|
Johannes Gäßler
|
b07791aa1d
test-opt: fix backend support check (#15317)
|
hai 5 meses |
 Georgi Gerganov
|
8b2483730f
tests : remove unused includes (ggml/0)
|
hai 5 meses |
 Jonathan Graehl
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
hai 5 meses |
|
Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
hai 8 meses |
 David Huang
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
hai 8 meses |
|
Georgi Gerganov
|
24203e9dd7
ggml : inttypes.h -> cinttypes (#0)
|
hai 1 ano |
|
Johannes Gäßler
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
hai 1 ano |
|
Georgi Gerganov
|
ab336a9d5e
code : normalize enum names (#5697)
|
hai 1 ano |
|
Georgi Gerganov
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
f93af02488
sync : ggml (conv 1d + 2d updates, UB fixes) (#3468)
|
%!s(int64=2) %!d(string=hai) anos |
 Cebtenzzre
|
bc39553c90
build : enable more non-default compiler warnings (#3200)
|
%!s(int64=2) %!d(string=hai) anos |
|
Cebtenzzre
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
%!s(int64=2) %!d(string=hai) anos |
 Eve
|
81844fbcfd
tests : Fix compilation warnings (Linux/GCC) (#2451)
|
%!s(int64=2) %!d(string=hai) anos |
