 slaren
|
e85bb1a8e7
llama : add functions to get the model's metadata (#4013)
|
2 years ago |
 Georgi Gerganov
|
4f447a4833
llama : fix data units (#4101)
|
2 years ago |
 Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
2 years ago |
 Jared Van Bortel
|
a6fc554e26
llama : restore prefix space in llama tokenizer (#4081)
|
2 years ago |
 Galunid
|
36eed0c42c
stablelm : StableLM support (#3586)
|
2 years ago |
|
Georgi Gerganov
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
2 years ago |
|
Kerfuffle
|
bb50a792ec
Add ReLU and SQR CUDA ops to (partially) fix Persimmon offloading (#4041)
|
2 years ago |
|
Galunid
|
df9d1293de
Unbreak persimmon after #3837 (#4010)
|
2 years ago |
 Meng Zhang
|
46876d2a2c
cuda : supports running on CPU for GGML_USE_CUBLAS=ON build (#3946)
|
2 years ago |
|
Meng Zhang
|
3d48f42efc
llama : mark LLM_ARCH_STARCODER as full offload supported (#3945)
|
2 years ago |
 cebtenzzre
|
3fdbe6b66b
llama : change yarn_ext_factor placeholder to -1 (#3922)
|
2 years ago |
|
Georgi Gerganov
|
1efae9b7dc
llm : prevent from 1-D tensors being GPU split (#3697)
|
2 years ago |
|
cebtenzzre
|
0eb332a10f
llama : fix llama_context_default_params after #2268 (#3893)
|
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
|
50337961a6
llm : add llm_build_context (#3881)
|
2 years ago |
 Andrew Godfrey
|
73bdcb395e
finetune : add -ngl parameter (#3762)
|
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 |
|
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 |
|
Georgi Gerganov
|
71a09da301
llama : fix kv shift bug (#3835)
|
2 years ago |
|
Georgi Gerganov
|
d69d777c02
ggml : quantization refactoring (#3833)
|
2 years ago |
|
Kerfuffle
|
bd6d9e2059
llama : allow quantizing k-quants to fall back when tensor size incompatible (#3747)
|
2 years ago |
|
Georgi Gerganov
|
fdee152e4e
starcoder : add GPU offloading (#3827)
|
2 years ago |
|
cebtenzzre
|
6d459cbfbe
llama : correctly report GGUFv3 format (#3818)
|
2 years ago |
|
Georgi Gerganov
|
2f9ec7e271
cuda : improve text-generation and batched decoding performance (#3776)
|
2 years ago |
 Marcus Dunn
|
5be6c803fa
llama : remove token functions with `context` args in favor of `model` (#3720)
|
2 years ago |
 goerch
|
9e70cc0322
Add test for MPT tokenization (#3728)
|
2 years ago |
