 slaren
|
7fe4678b02
llama : fix session save/load with quantized KV (#5649)
|
1 year ago |
|
slaren
|
ba2135ccae
gemma : allow offloading the output tensor (#5646)
|
1 year ago |
 Jared Van Bortel
|
89febfed93
examples : do not assume BOS when shifting context (#5622)
|
1 year ago |
 Georgi Gerganov
|
5022cf242d
sync : ggml
|
1 year ago |
 Pierrick Hymbert
|
1ecea255eb
server: health: fix race condition on slots data using tasks queue (#5634)
|
1 year ago |
 Ettore Di Giacinto
|
a00a35cef9
readme : add LocalAI to the availables UI (#5629)
|
1 year ago |
|
Georgi Gerganov
|
eccd7a26dd
sync : ggml (#5633)
|
1 year ago |
|
Georgi Gerganov
|
c14f72db9c
readme : update hot topics
|
1 year ago |
 Daniel Bevenius
|
cc6cac08e3
llava : add --skip-unknown to 1.6 convert.py (#5632)
|
1 year ago |
 postmasters
|
580111d42b
llama : add `gemma` model (#5631)
|
1 year ago |
 Meng, Hengyu
|
88c46cbdac
[SYCL] conext add name (#5624)
|
1 year ago |
 Kawrakow
|
a14679cc30
IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)
|
1 year ago |
 CJ Pais
|
6560bed3f0
server : support llava 1.6 (#5553)
|
1 year ago |
|
slaren
|
06bf2cf8c4
make : fix debug build with CUDA (#5616)
|
1 year ago |
|
Daniel Bevenius
|
4ed8e4fbef
llava : add explicit instructions for llava-1.6 (#5611)
|
1 year ago |
 Xuan Son Nguyen
|
9c405c9f9a
Server: use llama_chat_apply_template (#5593)
|
1 year ago |
 Dane Madsen
|
5207b3fbc5
readme : update UI list (#5605)
|
1 year ago |
 Haoxiang Fei
|
8dbbd75754
metal : add build system support for embedded metal library (#5604)
|
1 year ago |
|
Pierrick Hymbert
|
c0a8c6db37
server : health endpoint configurable failure on no slot (#5594)
|
1 year ago |
 AidanBeltonS
|
b9111bd209
Update ggml_sycl_op_mul_mat_vec_q (#5502)
|
1 year ago |
 Mathijs de Bruin
|
633782b8d9
nix: now that we can do so, allow MacOS to build Vulkan binaries
|
1 year ago |
 0cc4m
|
22f83f0c38
Enable Vulkan MacOS CI
|
1 year ago |
|
0cc4m
|
bb9dcd560a
Refactor validation and enumeration platform checks into functions to clean up ggml_vk_instance_init()
|
1 year ago |
|
0cc4m
|
f50db6ae0b
Add check for VK_KHR_portability_enumeration for MoltenVK support
|
1 year ago |
|
Mathijs de Bruin
|
d8c054517d
Add preprocessor checks for Apple devices.
|
1 year ago |
|
Mathijs de Bruin
|
42f664a382
Resolve ErrorIncompatibleDriver with Vulkan on MacOS.
|
1 year ago |
|
Mathijs de Bruin
|
5dde540897
Allow for Vulkan build with Accelerate.
|
1 year ago |
|
slaren
|
40c3a6c1e1
cuda : ignore peer access already enabled errors (#5597)
|
1 year ago |
|
Jared Van Bortel
|
f24ed14ee0
make : pass CPPFLAGS directly to nvcc, not via -Xcompiler (#5598)
|
1 year ago |
 nopperl
|
9d679f0fcc
examples : support minItems/maxItems in JSON grammar converter (#5039)
|
1 year ago |
