 Xuan Son Nguyen
|
6c5bc0625f
server : (refactoring) do not rely on JSON internally (#10643)
|
il y a 1 an |
 Plamen Minev
|
7736837d62
fix(server) : not show alert when DONE is received (#10674)
|
il y a 1 an |
 Jeff Bolz
|
c9c6e01dae
vulkan: Add VK_NV_cooperative_matrix2 support for mul_mat and flash attention (#10206)
|
il y a 1 an |
 Riccardo Orlando
|
6fe6247831
llama : add Minerva 7B model support (#10673)
|
il y a 1 an |
 Georgi Gerganov
|
0cd182ebcc
sync : ggml
|
il y a 1 an |
 PAB
|
a8cbab201d
ggml: add `GGML_SET` Metal kernel + i32 CPU kernel (ggml/1037)
|
il y a 1 an |
|
PAB
|
c2082d93a8
ggml : add `GGML_PAD_REFLECT_1D` operation (ggml/1034)
|
il y a 1 an |
 Daniel Bevenius
|
d405804be8
py : update outdated copy-paste instructions [no ci] (#10667)
|
il y a 1 an |
 aryantandon01
|
f112d198cd
Update deprecation-warning.cpp (#10619)
|
il y a 1 an |
|
Georgi Gerganov
|
1da7b76569
server : fix speculative decoding with context shift (#10641)
|
il y a 1 an |
 Diego Devesa
|
59f4db1088
ggml : add predefined list of CPU backend variants to build (#10626)
|
il y a 1 an |
|
Diego Devesa
|
2803540814
ggml-cpu : fix HWCAP2_I8MM value (#10646)
|
il y a 1 an |
 ltoniazzi
|
253b7fde91
Fix HF repo commit to clone lora test models (#10649)
|
il y a 1 an |
 JFLFY2255
|
8d0cfd554a
llama: Support MiniCPM-1B (with & w/o longrope) (#10559)
|
il y a 1 an |
|
Jeff Bolz
|
2759916d86
vulkan: Implement "fast divide" (mul+shift) for unary ops like copy (#10642)
|
il y a 1 an |
 Nicolò Scipione
|
40c6d79fb5
SYCL : Move to compile time oneMKL interface backend selection for NVIDIA backend (#10584)
|
il y a 1 an |
 Wang Ran (汪然)
|
98036d5670
fix typo of README.md (#10605)
|
il y a 1 an |
 Frankie Robertson
|
cd2f37b304
Avoid using __fp16 on ARM with old nvcc (#10616)
|
il y a 1 an |
 Benson Wong
|
da6aac91f1
Add docs for creating a static build (#10268) (#10630)
|
il y a 1 an |
 piDack
|
01e6d9bb71
clip : add sycl support (#10574)
|
il y a 1 an |
|
Jeff Bolz
|
cc98896db8
vulkan: optimize and reenable split_k (#10637)
|
il y a 1 an |
|
Xuan Son Nguyen
|
91c36c269b
server : (web ui) Various improvements, now use vite as bundler (#10599)
|
il y a 1 an |
|
Georgi Gerganov
|
1cd3df46bd
scripts : remove amx sync
|
il y a 1 an |
|
Georgi Gerganov
|
c505471857
sync : ggml
|
il y a 1 an |
 mahorozte
|
e9e661bd59
CUDA: remove unnecessary warp reduce in FA (ggml/1032)
|
il y a 1 an |
|
PAB
|
efb6ae9630
feat: add `GGML_UNARY_OP_ARGMAX` Metal kernel (ggml/1019)
|
il y a 1 an |
|
PAB
|
667d70d170
metal : add `GGML_OP_CONV_TRANSPOSE_1D` kernels (ggml/1026)
|
il y a 1 an |
|
Xuan Son Nguyen
|
3b4f2e33e2
llama : add missing LLAMA_API for llama_chat_builtin_templates (#10636)
|
il y a 1 an |
 Nikolaos Pothitos
|
82bca2257b
readme : add option, update default value, fix formatting (#10271)
|
il y a 1 an |
|
Georgi Gerganov
|
0115df2f65
metal : small-batch mat-mul kernels (#10581)
|
il y a 1 an |
