 Neuman Vong
|
704359e299
vulkan: Find optimal memory type but with fallback (#5381)
|
vor 1 Jahr |
 Rune
|
594fca3fef
readme : fix typo (#5490)
|
vor 1 Jahr |
 John
|
ccbb277f46
llava : update README.md (#5489)
|
vor 1 Jahr |
 Michael Podvitskiy
|
8084d55440
cmake : ARM intrinsics detection for MSVC (#5401)
|
vor 1 Jahr |
|
John
|
aa23412989
llava : support v1.6 (#5267)
|
vor 1 Jahr |
 AT
|
f5ca054855
Early return for zero size calls to get_tensor. (#5482)
|
vor 1 Jahr |
|
John
|
6c00a06692
gguf : add python reader example (#5216)
|
vor 1 Jahr |
 Jared Van Bortel
|
ea9c8e1143
llama : add support for Nomic Embed (#5468)
|
vor 1 Jahr |
 Aarni Koskela
|
c4e6dd59e4
llama : allow raw byte in SPM vocabs; don't crash on nl 404 (#5478)
|
vor 1 Jahr |
|
Aarni Koskela
|
037259be68
llama : make load error reporting more granular (#5477)
|
vor 1 Jahr |
 Daniel Bevenius
|
263978904c
finetune : rename feed-forward tensors (w1/w2/w3) (#4839)
|
vor 1 Jahr |
 Georgi Gerganov
|
cf45252a7c
tests : multi-thread the tokenizer tests (#5474)
|
vor 1 Jahr |
 Douglas Hanley
|
03bf161eb6
llama : support batched embeddings (#5466)
|
vor 1 Jahr |
 Johannes Gäßler
|
ad014bba97
make: add error message for bad CUDA version (#5444)
|
vor 1 Jahr |
|
Georgi Gerganov
|
49cc1f7d67
bert : add tests + fix quantization (#5475)
|
vor 1 Jahr |
|
Georgi Gerganov
|
99b8b43d7b
tests : disable moe test (#5473)
|
vor 1 Jahr |
 Kawrakow
|
895407f31b
ggml-quants : fix compiler warnings (shadow variable) (#5472)
|
vor 1 Jahr |
|
Georgi Gerganov
|
099afc6274
llama : fix quantization when tensors are missing (#5423)
|
vor 1 Jahr |
|
Georgi Gerganov
|
df334a1125
swift : package no longer use ggml dependency (#5465)
|
vor 1 Jahr |
 Lee
|
dbd8828eb0
py : fix persimmon `n_rot` conversion (#5460)
|
vor 1 Jahr |
 Abhilash Majumder
|
43fe07c1a4
ggml-sycl: Replace 3d ops with macro (#5458)
|
vor 1 Jahr |
|
Daniel Bevenius
|
4a46d2b792
llava : remove prog parameter from ArgumentParser (#5457)
|
vor 1 Jahr |
|
Georgi Gerganov
|
3b169441df
sync : ggml (#5452)
|
vor 1 Jahr |
|
Johannes Gäßler
|
3bdc4cd0f5
CUDA: mul_mat_vec_q tiling, refactor mul mat logic (#5434)
|
vor 1 Jahr |
|
Douglas Hanley
|
2891c8aa9a
Add support for BERT embedding models (#5423)
|
vor 1 Jahr |
 github-actions[bot]
|
97a336507e
flake.lock: Update
|
vor 1 Jahr |
 Sergio López
|
c88c74f967
vulkan: only use M-sized matmul on Apple GPUs (#5412)
|
vor 1 Jahr |
 Alexey Parfenov
|
a803333a4e
common : use enums for sampler types (#5418)
|
vor 1 Jahr |
|
Alexey Parfenov
|
684780141a
server : allow to specify tokens as strings in logit_bias (#5003)
|
vor 1 Jahr |
|
Georgi Gerganov
|
85910c5b30
main : ctrl+C print timing in non-interactive mode (#3873)
|
vor 1 Jahr |
