 Chenguang Li
|
a0f98dd604
CANN: Optimize RMS_NORM using cache (#15419)
|
5 miesięcy temu |
 Diego Devesa
|
54a241f505
sched : fix possible use of wrong ids tensor when offloading moe prompt processing (#15488)
|
5 miesięcy temu |
 Georgi Gerganov
|
cd36b5e5c7
llama : remove deprecated llama_kv_self API (#15472)
|
5 miesięcy temu |
|
Georgi Gerganov
|
3f196be84b
graph : remove build_attn_with_sinks overload (#15469)
|
5 miesięcy temu |
 Acly
|
97ae5961a4
vulkan : support conv_2d_dw with f16 weights (#15392)
|
5 miesięcy temu |
 Dong Won Kim
|
20c2dac8c6
vulkan: add exp operation (#15456)
|
5 miesięcy temu |
 Jeff Bolz
|
96452a3fa4
vulkan: Reuse conversion results in prealloc_y (#15410)
|
5 miesięcy temu |
 Jie Fu (傅杰)
|
9ad5e60dba
examples : fix some typos in examples/model-conversion/README.md (#15477)
|
5 miesięcy temu |
|
Georgi Gerganov
|
715a6db02c
kv-cache : drop the "unified" prefix (#15467)
|
5 miesięcy temu |
|
Jie Fu (傅杰)
|
ad294df03f
examples : install torch-cpu for model conversion tool/example (#15475)
|
5 miesięcy temu |
 Ali Tariq
|
029bb39eb1
ci : enable RVV1.0 native build (#15386)
|
5 miesięcy temu |
|
Georgi Gerganov
|
30649cab65
ci : continue file download with wget (#15471)
|
5 miesięcy temu |
 Daniel Bevenius
|
2758fa10da
examples : add model conversion tool/example (#15455)
|
5 miesięcy temu |
 Michael Giba
|
b108e42904
ci : fix -Werror=return-type in clip.cpp so ci/run.sh can run without issue (#15221)
|
5 miesięcy temu |
 Copilot
|
245be739df
ci : add copilot-instructions.md (#15286)
|
5 miesięcy temu |
 Julien Denize
|
b2caf67db1
convert : make Mistral community chat templates optional via parameter (#15420)
|
5 miesięcy temu |
|
Jie Fu (傅杰)
|
2f3dbffb17
common : fix incorrect print of non-ascii characters in the logging (#15466)
|
5 miesięcy temu |
 Xuan-Son Nguyen
|
945e1f12a6
ggml : fix condition of im2col on Metal backend (#15460)
|
5 miesięcy temu |
 stduhpf
|
1b0db8f6e0
server : fix webui (#15462)
|
5 miesięcy temu |
|
Daniel Bevenius
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
5 miesięcy temu |
 R0CKSTAR
|
8ad038c0fd
musa: add GGML_UNUSED_VARS (#15446)
|
5 miesięcy temu |
|
Diego Devesa
|
5682a3745f
sched : copy only the used experts when offloading prompt processing (#15346)
|
5 miesięcy temu |
 teo
|
1bc664a26a
server: fix OpenAI API compatibility for usage statistics in chat streams (#15444)
|
5 miesięcy temu |
 Johannes Gäßler
|
13aeb7aef2
CUDA: refactor FA support/selection code (#15454)
|
5 miesięcy temu |
|
Johannes Gäßler
|
7a6e91ad26
CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)
|
5 miesięcy temu |
|
Jeff Bolz
|
fec9519802
vulkan: shorten pipeline name strings (#15431)
|
5 miesięcy temu |
|
Daniel Bevenius
|
657b8a77bd
chat: handle gpt-oss return/end token inconsistency (#15421)
|
5 miesięcy temu |
 Jie Fu (傅杰)
|
ec5ab1a36c
common : fix context shift help message (#15448)
|
5 miesięcy temu |
 xiaobing318
|
1a99c2d948
cmake : fix target include directories (#15450)
|
5 miesięcy temu |
|
Daniel Bevenius
|
37f10f955f
make : remove make in favor of CMake (#15449)
|
5 miesięcy temu |
