 Alex Cheema
|
fecd081047
t
|
11 months ago |
|
Alex Cheema
|
49664c46c0
t
|
11 months ago |
|
Alex Cheema
|
2564d7c2b4
docker runner
|
11 months ago |
|
Alex Cheema
|
3313151010
test cuda
|
11 months ago |
|
Alex Cheema
|
a3b0650f30
use gpu.nvidia.medium
|
11 months ago |
|
Alex Cheema
|
3a0c9c8582
linux-cuda image
|
11 months ago |
|
Alex Cheema
|
af2f98bad4
run tinygrad tests on gpu.nvidia.small.gen2 (NVIDIA A10G 24GB)
|
11 months ago |
|
Alex Cheema
|
0fd6bd91a0
run tinygrad with llama-3-8b
|
11 months ago |
|
Alex Cheema
|
08e8cacf01
run integration test for each inference engine
|
11 months ago |
|
Alex Cheema
|
32bb44b3a2
request to both nodes in integration test, dont preload the model - exo should be robust against that
|
11 months ago |
|
Alex Cheema
|
2a8f1ae4c5
get rid of caches. circeci downloads fast enough
|
11 months ago |
|
Alex Cheema
|
67ad3f57a1
use llama 3.1 in tests
|
11 months ago |
|
Alex Cheema
|
92b66e275f
fix cache
|
11 months ago |
|
Alex Cheema
|
cf3dae9570
circleci: separate hf, tinygrad caches
|
11 months ago |
|
Alex Cheema
|
faadfa29dd
circleci chatgpt integration test
|
11 months ago |
|
Alex Cheema
|
9a03991f1a
cache key
|
11 months ago |
|
Alex Cheema
|
2065c7751a
orb
|
11 months ago |
|
Alex Cheema
|
cf4cddccc1
port github workflow to circleci
|
11 months ago |
 Alex Cheema
|
21b0bf8777
Update config.yml
|
11 months ago |
|
Alex Cheema
|
997fcaff35
CircleCI Commit
|
11 months ago |
