 Georgi Gerganov
|
ec2e10c444
llama : add llama_init_backend() API (close #1527)
|
2 years ago |
|
Georgi Gerganov
|
8a203f9fa1
llama : fix compile warnings in llama_set_state_data()
|
2 years ago |
|
Georgi Gerganov
|
2d5db48371
ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508)
|
2 years ago |
 Stephan Walter
|
dc271c52ed
Remove unused n_parts parameter (#1509)
|
2 years ago |
 Johannes Gäßler
|
905d87b70a
ggml : GPU-accelerated token generation (#1412)
|
2 years ago |
|
Georgi Gerganov
|
738ace394a
llama : free ggml context in set / copy state data (close #1425)
|
2 years ago |
|
Georgi Gerganov
|
b9fd7eee57
ggml : remove bit shuffling (#1405)
|
2 years ago |
 Jed Fox
|
3924088512
Remove default arguments from sampling functions (#1343)
|
2 years ago |
 Evan Jones
|
e216aa0463
llama : only copy used KV cache in get / set state (#1272)
|
2 years ago |
|
Georgi Gerganov
|
0e6cbff1b7
llama : fix compile warnings
|
2 years ago |
 Robert Brisita
|
2bb992f034
llama : allow 0 as a seed number. (#1275)
|
2 years ago |
|
Georgi Gerganov
|
70269cae37
llama : fix session load / save (#1263)
|
2 years ago |
 Alex Klinkhamer
|
90b19bd6ee
llama : let context be const when accessing const data (#1261)
|
2 years ago |
 Ivan Stepanov
|
dd7eff57d8
llama : new sampling algorithms (#1126)
|
2 years ago |
|
Stephan Walter
|
36d19a603b
Remove Q4_3 which is no better than Q5 (#1218)
|
2 years ago |
|
Evan Jones
|
1481a9cf25
llama : add session file format and saved sessions in main (#1169)
|
2 years ago |
|
Georgi Gerganov
|
574406dc7e
ggml : add Q5_0 and Q5_1 quantization (#1187)
|
2 years ago |
 Ásgeir Bjarni Ingvarsson
|
87a6f846d3
Allow setting the rng seed after initialization. (#1184)
|
2 years ago |
|
Georgi Gerganov
|
7a32fcb3b2
ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)
|
2 years ago |
|
Georgi Gerganov
|
c4fe84fb0d
llama : refactor get / set state + remove redundant kv cache API (#1143)
|
2 years ago |
 xaedes
|
b6e7f9b09e
llama : add api for getting/setting the complete state: rng, logits, embedding and kv_cache (#1105)
|
2 years ago |
 Kawrakow
|
38de86a711
llama : multi-threaded quantization (#1075)
|
2 years ago |
|
Georgi Gerganov
|
e0305ead3a
ggml : add Q4_3 quantization (#1082)
|
2 years ago |
|
Georgi Gerganov
|
77a73403ca
ggml : add new Q4_2 quantization (ARM only) (#1046)
|
2 years ago |
 slaren
|
315a95a4d3
Add LoRA support (#820)
|
2 years ago |
|
Georgi Gerganov
|
9190e8eac8
llama : merge llama_internal.h into llama.h
|
2 years ago |
|
Stephan Walter
|
e7f6997f89
Don't crash on ftype (formerly f16) == 4 (#917)
|
2 years ago |
|
Stephan Walter
|
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709)
|
2 years ago |
 comex
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 years ago |
 unbounded
|
62cfc54f77
Add quantize-stats command for testing quantization (#728)
|
2 years ago |
