 Jeff Bolz
|
330c3d2d21
vulkan: optimize mul_mat_id loading row ids into shared memory (#15427)
|
4 сар өмнө |
 Johannes Gäßler
|
e92734d51b
test-opt: allow slight inprecision (#15503)
|
4 сар өмнө |
 Reese Levine
|
45363632cb
ggml WebGPU: add support for quantization types (#15440)
|
4 сар өмнө |
 Aldehir Rojas
|
32732f2459
model : gpt-oss add response_format support (#15494)
|
4 сар өмнө |
 rmatif
|
92f7f0a53c
ggml: add `conv3d` op (#15182)
|
4 сар өмнө |
 Yavor Ivanov
|
b1ab91821f
cuda : add Pad Reflect 1D support (#14659)
|
4 сар өмнө |
 Georgi Gerganov
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
4 сар өмнө |
 Aaron Teo
|
ad5c975c2d
ggml-cpu: Support Q5_0 and Q5_1 on s390x (#15486)
|
4 сар өмнө |
 65a
|
4afb0a746f
server : Support multimodal completion and embeddings prompts in JSON format (#15108)
|
4 сар өмнө |
 Tarek Dakhran
|
e288693669
readme : model : mtdm : lfm2 improvements (#15476)
|
4 сар өмнө |
 Chenguang Li
|
a0f98dd604
CANN: Optimize RMS_NORM using cache (#15419)
|
4 сар өмнө |
 Diego Devesa
|
54a241f505
sched : fix possible use of wrong ids tensor when offloading moe prompt processing (#15488)
|
4 сар өмнө |
|
Georgi Gerganov
|
cd36b5e5c7
llama : remove deprecated llama_kv_self API (#15472)
|
4 сар өмнө |
|
Georgi Gerganov
|
3f196be84b
graph : remove build_attn_with_sinks overload (#15469)
|
4 сар өмнө |
 Acly
|
97ae5961a4
vulkan : support conv_2d_dw with f16 weights (#15392)
|
4 сар өмнө |
 Dong Won Kim
|
20c2dac8c6
vulkan: add exp operation (#15456)
|
4 сар өмнө |
|
Jeff Bolz
|
96452a3fa4
vulkan: Reuse conversion results in prealloc_y (#15410)
|
4 сар өмнө |
 Jie Fu (傅杰)
|
9ad5e60dba
examples : fix some typos in examples/model-conversion/README.md (#15477)
|
4 сар өмнө |
|
Georgi Gerganov
|
715a6db02c
kv-cache : drop the "unified" prefix (#15467)
|
4 сар өмнө |
|
Jie Fu (傅杰)
|
ad294df03f
examples : install torch-cpu for model conversion tool/example (#15475)
|
4 сар өмнө |
 Ali Tariq
|
029bb39eb1
ci : enable RVV1.0 native build (#15386)
|
4 сар өмнө |
|
Georgi Gerganov
|
30649cab65
ci : continue file download with wget (#15471)
|
4 сар өмнө |
 Daniel Bevenius
|
2758fa10da
examples : add model conversion tool/example (#15455)
|
4 сар өмнө |
 Michael Giba
|
b108e42904
ci : fix -Werror=return-type in clip.cpp so ci/run.sh can run without issue (#15221)
|
4 сар өмнө |
 Copilot
|
245be739df
ci : add copilot-instructions.md (#15286)
|
4 сар өмнө |
 Julien Denize
|
b2caf67db1
convert : make Mistral community chat templates optional via parameter (#15420)
|
4 сар өмнө |
|
Jie Fu (傅杰)
|
2f3dbffb17
common : fix incorrect print of non-ascii characters in the logging (#15466)
|
4 сар өмнө |
 Xuan-Son Nguyen
|
945e1f12a6
ggml : fix condition of im2col on Metal backend (#15460)
|
5 сар өмнө |
 stduhpf
|
1b0db8f6e0
server : fix webui (#15462)
|
5 сар өмнө |
|
Daniel Bevenius
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
5 сар өмнө |
