 Georgi Gerganov
|
1efae9b7dc
llm : prevent from 1-D tensors being GPU split (#3697)
|
2 years ago |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 years ago |
|
Georgi Gerganov
|
4d719a6d4e
cuda : check if this fixes Pascal card regression (#3882)
|
2 years ago |
|
Georgi Gerganov
|
183b3fac6c
metal : fix build errors and kernel sig after #2268 (#3898)
|
2 years ago |
|
cebtenzzre
|
2fffa0d61f
cuda : fix RoPE after #2268 (#3897)
|
2 years ago |
|
cebtenzzre
|
0eb332a10f
llama : fix llama_context_default_params after #2268 (#3893)
|
2 years ago |
 slaren
|
d02e98cde0
ggml-cuda : compute ptrs for cublasGemmBatchedEx in a kernel (#3891)
|
2 years ago |
|
cebtenzzre
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
2 years ago |
|
Georgi Gerganov
|
c43c2da8af
llm : fix llm_build_kqv taking unused tensor (benign, #3837)
|
2 years ago |
|
Georgi Gerganov
|
523e49b111
llm : fix falcon norm after refactoring (#3837)
|
2 years ago |
|
Georgi Gerganov
|
e16b9fa4ba
metal : multi-simd softmax (#3710)
|
2 years ago |
|
Georgi Gerganov
|
ff8f9a88da
common : minor (#3715)
|
2 years ago |
|
Georgi Gerganov
|
50337961a6
llm : add llm_build_context (#3881)
|
2 years ago |
 bandoti
|
0e40806c1c
common : allow caller to handle help/argument exceptions (#3715)
|
2 years ago |
 staviq
|
a2758d08e4
log : make generating separate log files optional (#3787)
|
2 years ago |
 l3utterfly
|
e75dfdd31b
sampling : null grammar field after reset (#3885)
|
2 years ago |
|
Georgi Gerganov
|
9a3b4f6c86
ggml : fix UNUSED macro (#3762)
|
2 years ago |
 Andrew Godfrey
|
73bdcb395e
finetune : add -ngl parameter (#3762)
|
2 years ago |
|
Georgi Gerganov
|
f0e209324a
scripts : add server-llm.sh (#3868)
|
2 years ago |
 Adrian Hesketh
|
ca190bca8e
server : re-enable completion and embedded at the same time (#3876)
|
2 years ago |
|
Georgi Gerganov
|
71e3718abd
llama : refactor graph build code (#3837)
|
2 years ago |
 kalomaze
|
238657db23
samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)
|
2 years ago |
 Tungsten842
|
07178c98e1
flake.nix: fix for rocm 5.7 (#3853)
|
2 years ago |
|
Georgi Gerganov
|
207b51900e
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)
|
2 years ago |
 Kerfuffle
|
6e08281e58
Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)
|
2 years ago |
|
cebtenzzre
|
2046eb4345
make : remove unnecessary dependency on build-info.h (#3842)
|
2 years ago |
|
Georgi Gerganov
|
71a09da301
llama : fix kv shift bug (#3835)
|
2 years ago |
|
Georgi Gerganov
|
d69d777c02
ggml : quantization refactoring (#3833)
|
2 years ago |
 Erik Scholz
|
ff3bad83e2
flake : update flake.lock for newer transformers version + provide extra dev shell (#3797)
|
2 years ago |
 Aarni Koskela
|
82a6646e02
metal : try cwd for ggml-metal.metal if bundle lookup fails (#3793)
|
2 years ago |
