 Johannes Gäßler
|
b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)
|
há 1 mês atrás |
 Xuan-Son Nguyen
|
6c2131773c
cli: new CLI experience (#17824)
|
há 1 mês atrás |
 Ali Tariq
|
4eba8d9451
ci : RVV1.0 builds with tests (#16682)
|
há 1 mês atrás |
 Diego Devesa
|
e072b2052e
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276)
|
há 1 mês atrás |
 sudhiarm
|
3fe36c3238
ci: add Arm-hosted Graviton4 runner (#17021)
|
há 2 meses atrás |
|
Johannes Gäßler
|
ee09828cb0
HIP: fix GPU_TARGETS (#16642)
|
há 3 meses atrás |
|
sudhiarm
|
2c0d875ae6
ci: add ARM64 Kleidiai build and test support (#16462)
|
há 3 meses atrás |
 Daniel Bevenius
|
04e632a4aa
ci : remove missing reranker model files (#16444)
|
há 3 meses atrás |
 Georgi Gerganov
|
bbd32bc038
ci : fix clean-up of old logs (#16381)
|
há 3 meses atrás |
|
Georgi Gerganov
|
d72f5f7ba2
ci : add AMD runners and workflows (#16249)
|
há 3 meses atrás |
 Eve
|
bee378e098
ci: run the x64 and arm ci on the github machines instead (#16183)
|
há 3 meses atrás |
|
Georgi Gerganov
|
0889589dbe
ci : enable Vulkan workflow on Mac (#16194)
|
há 3 meses atrás |
|
Georgi Gerganov
|
1d660d2fae
ci : use smaller model (#16168)
|
há 3 meses atrás |
|
Georgi Gerganov
|
4d0a7cbc61
ci : adjust params for less runtime (#16167)
|
há 3 meses atrás |
|
Georgi Gerganov
|
28baac9c9f
ci : migrate ggml ci to self-hosted runners (#16116)
|
há 3 meses atrás |
|
Georgi Gerganov
|
0320ac5264
metal : refactor + optimize v2 (#15995)
|
há 4 meses atrás |
|
Georgi Gerganov
|
55758b00ca
metal : refactor kernel loading (#15964)
|
há 4 meses atrás |
 Sigbjørn Skjæret
|
7d3c9f2b21
ci : explicitly set fa off or on (#15692)
|
há 4 meses atrás |
|
Georgi Gerganov
|
30649cab65
ci : continue file download with wget (#15471)
|
há 4 meses atrás |
 Reese Levine
|
21c021745d
ggml: Add initial WebGPU backend (#14521)
|
há 6 meses atrás |
 Vedran Miletić
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
há 6 meses atrás |
|
Sigbjørn Skjæret
|
88fc854b4b
llama : improve sep token handling (#14272)
|
há 7 meses atrás |
|
Diego Devesa
|
6adc3c3ebc
llama : add thread safety test (#14035)
|
há 7 meses atrás |
 pockers21
|
146b88e8b3
ci: fix CUDA build failure on autodl cloud machines (#14005)
|
há 7 meses atrás |
|
Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
há 8 meses atrás |
|
Xuan-Son Nguyen
|
e391d3ee8d
ci : no curl on ggml-ci (#12796)
|
há 9 meses atrás |
 Atharva Dubey
|
2004644b7a
ci : add env variable in ggml-ci and document the same in SYCL.md (#12736)
|
há 9 meses atrás |
 R0CKSTAR
|
492d7f1ff7
musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (#12611)
|
há 9 meses atrás |
|
R0CKSTAR
|
3cd3a39532
ci: [MUSA] add CI and update doc (#12562)
|
há 9 meses atrás |
 Akarshan Biswas
|
c95fa362b3
ci: [SYCL] ggml-ci Use main GPU and enable sysman (#12547)
|
há 9 meses atrás |
