 AlpinDale
|
2a349ca3e1
fix: specify device when loading lora and embedding tensors
|
6 mēneši atpakaļ |
 AlpinDale
|
98f9dbd734
feat: Triton Kernels for Punica (#613)
|
6 mēneši atpakaļ |
|
AlpinDale
|
f91991f584
fix: f-string fixes
|
7 mēneši atpakaļ |
|
AlpinDale
|
99680b2d23
feat: soft prompts (#589)
|
7 mēneši atpakaļ |
|
AlpinDale
|
0a6db357d8
fix: use safetensor keys instead of adapter_config.json to find unexpected modules
|
7 mēneši atpakaļ |
|
AlpinDale
|
85ef2fe8b1
chore: clean up placeholder symbols
|
7 mēneši atpakaļ |
|
AlpinDale
|
56e0b8223c
chore: add base class for LoRA-supported models
|
7 mēneši atpakaļ |
|
AlpinDale
|
25feb1d592
chore: add support for pinning lora adapters in the lru cache
|
7 mēneši atpakaļ |
|
AlpinDale
|
9e73559eba
make use of batched rotary embedding kernels to support long context lora
|
8 mēneši atpakaļ |
|
AlpinDale
|
eaa06fdd14
fix some f-strings
|
8 mēneši atpakaļ |
|
AlpinDale
|
b55381df0e
speedup lora loading times by resuing the cpu dummy lora
|
8 mēneši atpakaļ |
|
AlpinDale
|
e87c32bed3
feat: full tensor parallel for LoRA layers (#545)
|
8 mēneši atpakaļ |
|
AlpinDale
|
8be299e78b
fix: lora load check
|
10 mēneši atpakaļ |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 mēneši atpakaļ |
|
AlpinDale
|
e3252edd07
fix: remove event and stream, add typing (#382)
|
11 mēneši atpakaļ |
|
AlpinDale
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
1 gadu atpakaļ |
|
AlpinDale
|
657aec0cbd
refactor: OpenAI endpoint (#261)
|
1 gadu atpakaļ |
|
AlpinDale
|
697c06c4f5
fix: LoRA support for mixtral (#276)
|
1 gadu atpakaļ |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
1 gadu atpakaļ |
