 AlpinDale
|
8a6e83b52e
feat: fully sharded QKVParallelLinearWithLora support
|
5 달 전 |
|
AlpinDale
|
42d2ee0f43
chore: better error logging for unsupported lora weights
|
5 달 전 |
|
AlpinDale
|
c975bba905
fix: sharded state loader with lora
|
6 달 전 |
|
AlpinDale
|
9e73559eba
make use of batched rotary embedding kernels to support long context lora
|
6 달 전 |
 AlpinDale
|
e87c32bed3
feat: full tensor parallel for LoRA layers (#545)
|
6 달 전 |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 달 전 |
|
AlpinDale
|
657aec0cbd
refactor: OpenAI endpoint (#261)
|
11 달 전 |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
1 년 전 |
