 sudhiarm
|
2c0d875ae6
ci: add ARM64 Kleidiai build and test support (#16462)
|
hace 3 meses |
 Chenguang Li
|
aa4711d369
CANN: Improve ACL graph matching (#16166)
|
hace 3 meses |
 Charles Xu
|
d80d6d2400
kleidiai: kernel interface refactoring (#16460)
|
hace 3 meses |
 Neo Zhang Jianyu
|
b260213755
[SYCL] refactor soft_max, add soft_max_back (#16472)
|
hace 3 meses |
 Saba Fallah
|
e08db42595
model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)
|
hace 3 meses |
 Pascal
|
12bbc3fa50
refactor: centralize CoT parsing in backend for streaming mode (#16394)
|
hace 3 meses |
 ai-fonsi
|
9d0882840e
Disable CUDA host buffers on integrated GPUs (#16308)
|
hace 3 meses |
 issixx
|
d2ee056e1d
server : fix cancel pending task (#16467)
|
hace 3 meses |
 Georgi Gerganov
|
b2c08c9ec4
metal : mark FA blocks (#16372)
|
hace 3 meses |
|
Georgi Gerganov
|
7fdd16b432
server : improve context checkpoint logic (#16440)
|
hace 3 meses |
 Reese Levine
|
74b8fc17f9
ggml webgpu: profiling, CI updates, reworking of command submission (#16452)
|
hace 3 meses |
 Tarek Dakhran
|
aeaf8a36f0
llama : support LiquidAI LFM2-MoE hybrid model (#16464)
|
hace 3 meses |
|
Georgi Gerganov
|
df1b612e29
server : add `/v1/health` endpoint (#16461)
|
hace 3 meses |
 Sascha Rogmann
|
4e0388aa8a
webui : added download action (#13552) (#16282)
|
hace 3 meses |
|
Georgi Gerganov
|
ef4c5b87ea
presets : fix pooling param for embedding models (#16455)
|
hace 3 meses |
 Radoslav Gerganov
|
c61ae20d05
rpc : update documentation (#16441)
|
hace 3 meses |
|
Georgi Gerganov
|
0123ff38f5
memory : use sequential equal splits for recurrent modules (#16442)
|
hace 3 meses |
|
Georgi Gerganov
|
0a319bb75e
metal : add support for non-padded FA KV (#16148)
|
hace 3 meses |
|
Georgi Gerganov
|
1d6092fc72
tests : add -INF blocks to the KQ mask in the FA tests (#16380)
|
hace 3 meses |
|
Georgi Gerganov
|
8ae32dc9ec
metal : various optimizations + refactoring (#16446)
|
hace 3 meses |
 Gadflyii
|
3df2244df4
llama : add --no-host to disable host buffers (#16310)
|
hace 3 meses |
 Gabe Goodhart
|
c08002a198
chat : Granite Docling stopping (#16438)
|
hace 3 meses |
 Sigbjørn Skjæret
|
3a002afafa
ci : refactor sdk caching to minimize storage (#16414)
|
hace 3 meses |
|
Georgi Gerganov
|
a23b9bdbd3
ggml : fix unaligned access in AMX code (#16315)
|
hace 3 meses |
 Daniel Bevenius
|
04e632a4aa
ci : remove missing reranker model files (#16444)
|
hace 3 meses |
|
Daniel Bevenius
|
a80ff183ab
ggml-cpu : fix leftover handling in ggml_vec_scale_f32 for SVE (#16443)
|
hace 3 meses |
 Yuannan
|
1d49ca3759
nix : removed metal for nix (#16118)
|
hace 3 meses |
 Oleksandr Kuvshynov
|
c5fef0fcea
server: update readme to mention n_past_max metric (#16436)
|
hace 3 meses |
|
Gabe Goodhart
|
ca71fb9b36
model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206)
|
hace 3 meses |
|
Reese Levine
|
35266573b9
ggml webgpu: actually add softmax, fix rms_norm offset (#16400)
|
hace 3 meses |
