 Kawrakow
|
bd2d4e393b
1.5 bit quantization (#5453)
|
1 year ago |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 year ago |
 Douglas Hanley
|
4524290e87
Use correct type of pooling for embedding models (#5500)
|
1 year ago |
|
Douglas Hanley
|
03bf161eb6
llama : support batched embeddings (#5466)
|
1 year ago |
|
Douglas Hanley
|
2891c8aa9a
Add support for BERT embedding models (#5423)
|
1 year ago |
 Jared Van Bortel
|
1ec3332ade
YaRN : store rope scaling type as int32_t in memory (#5285)
|
1 year ago |
 Georgi Gerganov
|
5cb04dbc16
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
|
2 years ago |
|
Kawrakow
|
f4d7e54974
SOTA 3-bit quants (#5196)
|
2 years ago |
|
Jared Van Bortel
|
fbf1ddec69
Nomic Vulkan backend (#4456)
|
2 years ago |
 0cc4m
|
2307523d32
ggml : add Vulkan backend (#2059)
|
2 years ago |
 Abhilash Majumder
|
0f648573dd
ggml : add unified SYCL backend for Intel GPUs (#2690)
|
2 years ago |
 l3utterfly
|
5eaf9964fc
llama : dynamic temperature sampling (#4972)
|
2 years ago |
|
Kawrakow
|
66d575c45c
llama : add Q3_K_XS (#5060)
|
2 years ago |
|
Georgi Gerganov
|
44a1a4a41a
backend : add eval callback (#4935)
|
2 years ago |
 David Friehs
|
4483396751
llama : apply classifier-free guidance to logits directly (#4951)
|
2 years ago |
|
Kawrakow
|
147b17ac94
2-bit quantizations (#4897)
|
2 years ago |
|
David Friehs
|
df845cc982
llama : minimize size used for state save/load (#4820)
|
2 years ago |
 slaren
|
e7e4df031b
llama : ggml-backend integration (#4766)
|
2 years ago |
|
Kawrakow
|
469e75d0a3
llama : restore intended k-quants mixes for MoE models (#4872)
|
2 years ago |
|
Kawrakow
|
49662cbed3
ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)
|
2 years ago |
|
Kawrakow
|
dd5ae06405
SOTA 2-bit quants (#4773)
|
2 years ago |
|
Georgi Gerganov
|
52531fdff8
main : add self-extend support (#4815)
|
2 years ago |
|
Georgi Gerganov
|
b0034d93ce
examples : add passkey test (#3856)
|
2 years ago |
 Marcus Dunn
|
0040d42eeb
llama : replace all API facing `int`'s with `int32_t` (#4577)
|
2 years ago |
 crasm
|
c7e9701f86
llama : add ability to cancel model loading (#4462)
|
2 years ago |
|
Marcus Dunn
|
31f27758fa
llama : allow getting n_batch from llama_context in c api (#4540)
|
2 years ago |
|
slaren
|
c6c4fc081c
lora : add support for non-llama models (#3333)
|
2 years ago |
|
crasm
|
6391817cd1
llama : document logits_all deprecation (#4418)
|
2 years ago |
|
Georgi Gerganov
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
2 years ago |
 Kerfuffle
|
5aa365d88f
llama : allow overriding GGUF metadata when loading model (#4092)
|
2 years ago |
