 Alexander Borzunov
|
3c523ab0d2
Fix TP crashing when hypo_ids are used (#249)
|
2 rokov pred |
 justheuristic
|
c4938bc23e
Merge inference pools into one to increase inference speed (#225)
|
2 rokov pred |
|
justheuristic
|
5f58f00649
Return available cache size in rpc_info() (#191)
|
2 rokov pred |
|
justheuristic
|
ae9e71fe8e
Add local tensor-parallel fwd/bwd (#143)
|
2 rokov pred |
|
Alexander Borzunov
|
7cdc57a04b
Alloc inference cache as one contiguous buffer (#160)
|
2 rokov pred |
|
Alexander Borzunov
|
668b736031
Fix logging: do not duplicate lines, enable colors in Colab (#156)
|
2 rokov pred |
|
justheuristic
|
b04982c1a2
Bump transformers to 4.25.1 (#151)
|
2 rokov pred |
|
Alexander Borzunov
|
e4dc938dfe
Fix OOMs during server rebalancing (#150)
|
2 rokov pred |
|
Alexander Borzunov
|
e99bf36647
Use common folder for all caches, make it a volume in Dockerfile (#141)
|
2 rokov pred |
 Max Ryabinin
|
9faf08b898
Remove unused imports, add missing arguments to docstrings (#108)
|
2 rokov pred |
|
Alexander Borzunov
|
43ac6016ac
Fix dtypes in backend schemas (#99)
|
2 rokov pred |
|
Alexander Borzunov
|
7bd5916744
Make Petals a pip-installable package (attempt 2) (#102)
|
2 rokov pred |
