 Georgi Gerganov
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
1 rok temu |
|
Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
1 rok temu |
|
Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
1 rok temu |
 Diego Devesa
|
7eee341bee
common : use common_ prefix for common library functions (#9805)
|
1 rok temu |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
1 rok temu |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
1 rok temu |
 Xuan Son Nguyen
|
bfe76d4a17
common : move arg parser code to `arg.cpp` (#9388)
|
1 rok temu |
|
slaren
|
5fb5e24811
llama : minor sampling refactor (2) (#9386)
|
1 rok temu |
|
Xuan Son Nguyen
|
1b9ae5189c
common : refactor arg parser (#9308)
|
1 rok temu |
|
Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
1 rok temu |
 Masaya, Kato
|
da3913d8f9
batched: fix n_predict parameter (#8527)
|
1 rok temu |
 fairydreaming
|
807b0c49ff
Inference support for T5 and FLAN-T5 model families (#5763)
|
1 rok temu |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
1 rok temu |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
1 rok temu |
 Pedro Cuenca
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 rok temu |
|
Georgi Gerganov
|
95d576b48e
metal : pad n_ctx by 32 (#6177)
|
1 rok temu |
|
Georgi Gerganov
|
05b06210c9
llama : more consistent names of count variables (#5994)
|
1 rok temu |
 compilade
|
c2101a2e90
llama : support Mamba Selective State Space Models (#5328)
|
1 rok temu |
 Herman Semenov
|
5d3de51f97
ggml, common, examples, tests : fixed type arguments in printf (#5528)
|
1 rok temu |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 rok temu |
|
Georgi Gerganov
|
b0034d93ce
examples : add passkey test (#3856)
|
2 lat temu |
|
Georgi Gerganov
|
2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749)
|
2 lat temu |
 Marcus Dunn
|
5be6c803fa
llama : remove token functions with `context` args in favor of `model` (#3720)
|
2 lat temu |
|
Georgi Gerganov
|
22c69a2794
batched : add len CLI argument
|
2 lat temu |
|
Georgi Gerganov
|
0e89203b51
speculative : add tree-based sampling example (#3624)
|
2 lat temu |
|
Georgi Gerganov
|
8c70a5ff25
batched : add bench tool (#3545)
|
2 lat temu |
|
slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
2 lat temu |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
2 lat temu |
