 Stephan Walter
|
1b107b8550
ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)
|
2 anni fa |
 Didzis Gosko
|
527b6fba1d
llama : make model stateless and context stateful (llama_state) (#1797)
|
2 anni fa |
 Borislav Stanimirov
|
9cbf50c041
build : fix and ignore MSVC warnings (#1889)
|
2 anni fa |
 Kawrakow
|
99009e72f8
ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684)
|
2 anni fa |
|
Stephan Walter
|
dc271c52ed
Remove unused n_parts parameter (#1509)
|
2 anni fa |
 DannyDaemonic
|
f4cef87edf
Add git-based build information for better issue tracking (#1232)
|
2 anni fa |
|
Kawrakow
|
38de86a711
llama : multi-threaded quantization (#1075)
|
2 anni fa |
 Georgi Gerganov
|
eb17a026fd
quantize-stats : fix bug in --type argument
|
2 anni fa |
 Pavol Rusnak
|
c56b715269
Expose type name from ggml (#970)
|
2 anni fa |
|
Georgi Gerganov
|
9190e8eac8
llama : merge llama_internal.h into llama.h
|
2 anni fa |
 comex
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 anni fa |
 unbounded
|
62cfc54f77
Add quantize-stats command for testing quantization (#728)
|
2 anni fa |
