 slaren
|
06abf8eeba
ggml : add view_src and view_offs to ggml_tensor for views (#2874)
|
2 lat temu |
 xaedes
|
44c117f41e
train : mem usage and other improvements (#2439)
|
2 lat temu |
 Georgi Gerganov
|
35feac6560
ggml : sync (mem align to header + conv_transpose_2d fixes + ggml_alloc) (#2852)
|
2 lat temu |
 Shouzheng Liu
|
b91ad7f461
ggml-alloc : enlarge size of parse_seq (#2776)
|
2 lat temu |
|
Shouzheng Liu
|
38b16dfca6
metal : bug-fix when enable ggml-alloc (#2757)
|
2 lat temu |
|
Georgi Gerganov
|
cf658adc83
llm : add Falcon support (#2717)
|
2 lat temu |
|
Georgi Gerganov
|
ef3f333d37
ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709)
|
2 lat temu |
|
Shouzheng Liu
|
a872a2b28e
ggml-alloc : fix discrepency between measure&eval (#2639)
|
2 lat temu |
|
Shouzheng Liu
|
fc8ef549e5
metal : enable ggml-alloc (#2627)
|
2 lat temu |
 Sam Spilsbury
|
916a9acdd0
ggml-alloc: Don't try to re-use buffers of external tensors (#2562)
|
2 lat temu |
|
slaren
|
a113689571
ggml : add graph tensor allocator (#2411)
|
2 lat temu |
