Stephan Walter
|
36d19a603b
Remove Q4_3 which is no better than Q5 (#1218)
|
2 vuotta sitten |
Georgi Gerganov
|
574406dc7e
ggml : add Q5_0 and Q5_1 quantization (#1187)
|
2 vuotta sitten |
Pavol Rusnak
|
859fee6dfb
quantize : use `map` to assign quantization type from `string` (#1191)
|
2 vuotta sitten |
Georgi Gerganov
|
7a32fcb3b2
ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)
|
2 vuotta sitten |
Kawrakow
|
38de86a711
llama : multi-threaded quantization (#1075)
|
2 vuotta sitten |
Georgi Gerganov
|
e0305ead3a
ggml : add Q4_3 quantization (#1082)
|
2 vuotta sitten |
Georgi Gerganov
|
77a73403ca
ggml : add new Q4_2 quantization (ARM only) (#1046)
|
2 vuotta sitten |
Stephan Walter
|
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709)
|
2 vuotta sitten |
Slaren
|
64bde3ffd4
Fix ggml_init_params in quantize
|
2 vuotta sitten |
Stephan Walter
|
436e561931
all : be more strict about converting float to double (#458)
|
2 vuotta sitten |
Stephan Walter
|
c1f885067c
ggml : introduce structs for the q4 data blocks (#356)
|
2 vuotta sitten |
Georgi Gerganov
|
a316a425d0
Overhaul the examples structure
|
2 vuotta sitten |