 wwoodsTM
|
ff252ea48e
llama : add DRY sampler (#9702)
|
1 anno fa |
 Michael Podvitskiy
|
d80fb71f8b
llama: string_split fix (#10022)
|
1 anno fa |
 Srihari-mcw
|
2f8bd2b901
llamafile : extend sgemm.cpp support for Q5_0 models (#10010)
|
1 anno fa |
 Georgi Gerganov
|
bc5ba007b2
server : check that the prompt fits in the slot's context (#10030)
|
1 anno fa |
 Xuan Son Nguyen
|
958367bf53
server : refactor slot input data, move tokenizer to HTTP thread (#10023)
|
1 anno fa |
|
Georgi Gerganov
|
40f2555797
ci : fix cmake flags for SYCL
|
1 anno fa |
 Johannes Gäßler
|
167a515651
CUDA: fix insufficient buffer clearing for MMQ (#10032)
|
1 anno fa |
|
Johannes Gäßler
|
c39665f589
CUDA: fix MMQ for non-contiguous src0, add tests (#10021)
|
1 anno fa |
|
wwoodsTM
|
0a1c750c80
server : samplers accept the prompt correctly (#10019)
|
1 anno fa |
|
Georgi Gerganov
|
190a37d797
sync : ggml
|
1 anno fa |
|
Georgi Gerganov
|
2d3aba9ee8
llama.vim : bump generation time limit to 3s [no ci]
|
1 anno fa |
|
Johannes Gäßler
|
80273a306d
CUDA: fix 1D im2col, add tests (ggml/993)
|
1 anno fa |
 Daniel Bevenius
|
c19af0acb1
ggml : remove redundant set of contexts used field (ggml/978)
|
1 anno fa |
 Michael Coppola
|
ac113a0fee
llama.vim : add classic vim support (#9995)
|
1 anno fa |
 Jun Hee Yoo
|
4c9388fb96
metal : add POOL2D and fix IM2COL (#9943)
|
1 anno fa |
 github-actions[bot]
|
873279b159
flake.lock: Update
|
1 anno fa |
|
Xuan Son Nguyen
|
c8c07d658a
llama : fix empty batch causing llama_batch_allocr to crash (#9966)
|
1 anno fa |
|
Daniel Bevenius
|
19d900a756
llama : rename batch to ubatch (#9950)
|
1 anno fa |
 Molly Sophia
|
11d47057a5
Rwkv chat template fix (#10001)
|
1 anno fa |
|
Xuan Son Nguyen
|
c421ac072d
lora : warn user if new token is added in the adapter (#9948)
|
1 anno fa |
|
Molly Sophia
|
4ff7fe1fb3
llama : add chat template for RWKV-World + fix EOT (#9968)
|
1 anno fa |
 leo-pony
|
6b8447352d
[CANN] Adapt to dynamically loadable backends mechanism (#9970)
|
1 anno fa |
|
Daniel Bevenius
|
674804a996
arg : fix typo in embeddings argument help [no ci] (#9994)
|
1 anno fa |
|
Georgi Gerganov
|
e94a138d64
llama.vim : fix info text display [no ci] (#9787)
|
1 anno fa |
|
Georgi Gerganov
|
e01c67affe
llama.vim : move info to the right of screen [no ci] (#9787)
|
1 anno fa |
 Asghar Ghorbani
|
994cfb1acb
readme : update UI list (#9972)
|
1 anno fa |
|
Daniel Bevenius
|
94008cc760
arg : fix attention non-causal arg value hint (#9985)
|
1 anno fa |
|
Georgi Gerganov
|
dbd5f2f573
llama.vim : plugin for Neovim (#9787)
|
1 anno fa |
|
Georgi Gerganov
|
f594bc80ba
ggml : add asserts for type conversion in fattn kernels (#9971)
|
1 anno fa |
 Radoslav Gerganov
|
d5ebd79c76
rpc : pack only RPC structs (#9959)
|
1 anno fa |
