 Georgi Gerganov
|
7a32fcb3b2
ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)
|
2 lat temu |
 Kawrakow
|
38de86a711
llama : multi-threaded quantization (#1075)
|
2 lat temu |
|
Georgi Gerganov
|
e0305ead3a
ggml : add Q4_3 quantization (#1082)
|
2 lat temu |
|
Georgi Gerganov
|
77a73403ca
ggml : add new Q4_2 quantization (ARM only) (#1046)
|
2 lat temu |
 Stephan Walter
|
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709)
|
2 lat temu |
 Slaren
|
64bde3ffd4
Fix ggml_init_params in quantize
|
2 lat temu |
|
Stephan Walter
|
436e561931
all : be more strict about converting float to double (#458)
|
2 lat temu |
|
Stephan Walter
|
c1f885067c
ggml : introduce structs for the q4 data blocks (#356)
|
2 lat temu |
|
Georgi Gerganov
|
a316a425d0
Overhaul the examples structure
|
2 lat temu |
