Make local inference limits and workstation setup reproducible
This commit is contained in:
1 parent
7006991843
commit
8544abd2d4
28 files changed
+1022
-21
No files matched your search
+1
-1
@@ -16,7 +16,7 @@ OPTIONS = """--model --hf-repo --mmproj --alias --host --port --ctx-size --paral
|
||||
--jinja --reasoning --reasoning-budget --reasoning-preserve --no-reasoning-preserve --flash-attn --threads
|
||||
--threads-batch --n-gpu-layers --fit --fit-target --cache-type-k --cache-type-v
|
||||
--sleep-idle-seconds --image-min-tokens --cors-origins --no-ui --rope-scaling --rope-scale --yarn-orig-ctx
|
||||
--device --no-op-offload --no-kv-offload"""
|
||||
--device --no-op-offload --no-kv-offload --n-predict"""
|
||||
|
||||
|
||||
class LlamaTests(unittest.TestCase):
|
||||
|
||||
Reference in new issue
Block a user