 Adrien Gallouët
|
f709c7a33f
ci, tests : use cmake to download models and remove libcurl dependency (#18791)
|
2 weeks ago |
 Georgi Gerganov
|
84ae04f163
tests : refactor test-backend-sampler (#18753)
|
2 weeks ago |
 Reese Levine
|
15bff84bf5
ggml webgpu: initial flashattention implementation (#18610)
|
2 weeks ago |
 Daniel Bevenius
|
d3dce4e0a5
sampling : add support for backend sampling (#17004)
|
3 weeks ago |
 Johannes Gäßler
|
b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)
|
1 month ago |
 Xuan-Son Nguyen
|
6c2131773c
cli: new CLI experience (#17824)
|
1 month ago |
 Ali Tariq
|
4eba8d9451
ci : RVV1.0 builds with tests (#16682)
|
1 month ago |
 Diego Devesa
|
e072b2052e
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276)
|
2 months ago |
 sudhiarm
|
3fe36c3238
ci: add Arm-hosted Graviton4 runner (#17021)
|
2 months ago |
|
Johannes Gäßler
|
ee09828cb0
HIP: fix GPU_TARGETS (#16642)
|
3 months ago |
|
sudhiarm
|
2c0d875ae6
ci: add ARM64 Kleidiai build and test support (#16462)
|
3 months ago |
|
Daniel Bevenius
|
04e632a4aa
ci : remove missing reranker model files (#16444)
|
3 months ago |
|
Georgi Gerganov
|
bbd32bc038
ci : fix clean-up of old logs (#16381)
|
3 months ago |
|
Georgi Gerganov
|
d72f5f7ba2
ci : add AMD runners and workflows (#16249)
|
4 months ago |
 Eve
|
bee378e098
ci: run the x64 and arm ci on the github machines instead (#16183)
|
4 months ago |
|
Georgi Gerganov
|
0889589dbe
ci : enable Vulkan workflow on Mac (#16194)
|
4 months ago |
|
Georgi Gerganov
|
1d660d2fae
ci : use smaller model (#16168)
|
4 months ago |
|
Georgi Gerganov
|
4d0a7cbc61
ci : adjust params for less runtime (#16167)
|
4 months ago |
|
Georgi Gerganov
|
28baac9c9f
ci : migrate ggml ci to self-hosted runners (#16116)
|
4 months ago |
|
Georgi Gerganov
|
0320ac5264
metal : refactor + optimize v2 (#15995)
|
4 months ago |
|
Georgi Gerganov
|
55758b00ca
metal : refactor kernel loading (#15964)
|
4 months ago |
 Sigbjørn Skjæret
|
7d3c9f2b21
ci : explicitly set fa off or on (#15692)
|
5 months ago |
|
Georgi Gerganov
|
30649cab65
ci : continue file download with wget (#15471)
|
5 months ago |
|
Reese Levine
|
21c021745d
ggml: Add initial WebGPU backend (#14521)
|
6 months ago |
 Vedran Miletić
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
7 months ago |
|
Sigbjørn Skjæret
|
88fc854b4b
llama : improve sep token handling (#14272)
|
7 months ago |
|
Diego Devesa
|
6adc3c3ebc
llama : add thread safety test (#14035)
|
7 months ago |
 pockers21
|
146b88e8b3
ci: fix CUDA build failure on autodl cloud machines (#14005)
|
7 months ago |
|
Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
9 months ago |
|
Xuan-Son Nguyen
|
e391d3ee8d
ci : no curl on ggml-ci (#12796)
|
9 months ago |
