 Karol Kontny
|
4d3465c5ae
ggml: Fix data race in ggml threadpool (#11736)
|
11 месяцев назад |
 Johannes Gäßler
|
d80be897ac
CUDA: fix min. version for movmatrix (#11751)
|
11 месяцев назад |
 Nikolaos Pothitos
|
3ab410f55f
readme : update front-end framework (#11753)
|
11 месяцев назад |
 Xuan-Son Nguyen
|
0cf867160c
server : (webui) fix numeric settings being saved as string (#11739)
|
11 месяцев назад |
 Eric Curtin
|
d2fe216fb2
Make logging more verbose (#11714)
|
11 месяцев назад |
 Georgi Gerganov
|
ed926d8833
llama : fix defrag logic (#11707)
|
11 месяцев назад |
 Christian Fillion
|
2d219b389e
vocab : ignore invalid UTF-8 input in the BPE tokenizer (#11729)
|
11 месяцев назад |
 magicse
|
333820d749
llama : fix progress dots (#11730)
|
11 месяцев назад |
 Jeff Bolz
|
c026ba3c23
vulkan: print shared memory size (#11719)
|
11 месяцев назад |
|
Christian Fillion
|
7ee953a64a
llama : add llama_sampler_init for safe usage of llama_sampler_free (#11727)
|
11 месяцев назад |
 Akarshan Biswas
|
ec3bc8270b
SYCL: remove XMX info from print devices (#11712)
|
11 месяцев назад |
 Daniel Bevenius
|
b7552cfcbc
common : add default embeddings presets (#11677)
|
11 месяцев назад |
 Jinyang He
|
225bbbfa39
ggml : optimize and build warning fix for LoongArch (#11709)
|
11 месяцев назад |
 tv1wnd
|
855cd0734a
llama : fix old glm4 models (#11670)
|
11 месяцев назад |
|
Georgi Gerganov
|
8a59053f63
sync : ggml
|
11 месяцев назад |
 Patrick Peng
|
1d20e53c40
rpc: fix known RCE in rpc-server (ggml/1103)
|
11 месяцев назад |
|
Xuan-Son Nguyen
|
2fb3c32a16
server : (webui) migrate project to ReactJS with typescript (#11688)
|
11 месяцев назад |
 Tei Home
|
9ab42dc722
docs: update fedora cuda guide for 12.8 release (#11393)
|
11 месяцев назад |
|
Akarshan Biswas
|
194b2e69f8
SYCL: Adjust support condition for norm operators (#11674)
|
11 месяцев назад |
|
Georgi Gerganov
|
9dd7a0390f
llama : add log about loading model tensors (#11699)
|
11 месяцев назад |
 Adrien Gallouët
|
c0d4843225
build : fix llama.pc (#11658)
|
11 месяцев назад |
 junchao-zhao
|
8d4d2be143
ggml : fix LoongArch compile error with 128-bit SIMD (#11701)
|
11 месяцев назад |
|
Jeff Bolz
|
2c6c8df56d
vulkan: optimize coopmat2 iq2/iq3 callbacks (#11521)
|
11 месяцев назад |
 Rémy O
|
8a7e3bf17a
vulkan: initial support for IQ4_XS quantization (#11501)
|
11 месяцев назад |
|
Jeff Bolz
|
1b598b3058
vulkan: use smaller combined allocations to avoid fragmentation (#11551)
|
11 месяцев назад |
 Charles Duffy
|
902368a06b
metal : avoid breaking build when metal API predates TARGET_OS_VISION (#11690)
|
11 месяцев назад |
 Matvey Soloviev
|
c3db0480bb
readme : add link to Autopen under UIs (#11684)
|
11 месяцев назад |
|
Georgi Gerganov
|
d774ab3acc
metal : adjust support conditions for norm operators (#11671)
|
11 месяцев назад |
|
Johannes Gäßler
|
fa62da9b2d
CUDA: support for mat. mul. with ne03 != ne13 (#11656)
|
11 месяцев назад |
 SAMI
|
1ec208083c
llava: add quantization for the visual projector LLAVA, Qwen2VL (#11644)
|
11 месяцев назад |
