 Georgi Gerganov
|
95d576b48e
metal : pad n_ctx by 32 (#6177)
|
1 anno fa |
|
Georgi Gerganov
|
05b06210c9
llama : more consistent names of count variables (#5994)
|
1 anno fa |
 compilade
|
c2101a2e90
llama : support Mamba Selective State Space Models (#5328)
|
1 anno fa |
 Herman Semenov
|
5d3de51f97
ggml, common, examples, tests : fixed type arguments in printf (#5528)
|
1 anno fa |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 anno fa |
|
Georgi Gerganov
|
b0034d93ce
examples : add passkey test (#3856)
|
2 anni fa |
|
Georgi Gerganov
|
2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749)
|
2 anni fa |
 Marcus Dunn
|
5be6c803fa
llama : remove token functions with `context` args in favor of `model` (#3720)
|
2 anni fa |
|
Georgi Gerganov
|
22c69a2794
batched : add len CLI argument
|
2 anni fa |
|
Georgi Gerganov
|
0e89203b51
speculative : add tree-based sampling example (#3624)
|
2 anni fa |
|
Georgi Gerganov
|
8c70a5ff25
batched : add bench tool (#3545)
|
2 anni fa |
 slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
2 anni fa |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
2 anni fa |
