AlpinDale
|
18b45266bb
feat: add nemotron HF support (#606)
|
4 months ago |
AlpinDale
|
5761ef8c35
feat: gemma-2 support
|
5 months ago |
AlpinDale
|
4599c98f99
feat: dynamic image size support for VLMs
|
5 months ago |
AlpinDale
|
bbde979ecd
DeepSeek-V2 (#579)
|
5 months ago |
AlpinDale
|
7d3da17e19
fix: phi3 rope scaling
|
5 months ago |
AlpinDale
|
6a57861fca
feat: initial XPU support via intel_extension_for_pytorch (#571)
|
5 months ago |
AlpinDale
|
fe21123a1c
feat: TPU support (#570)
|
5 months ago |
AlpinDale
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
5 months ago |
AlpinDale
|
814c1ddeba
feat: add CustomOp interface for device portability
|
5 months ago |
AlpinDale
|
9e73559eba
make use of batched rotary embedding kernels to support long context lora
|
6 months ago |
AlpinDale
|
14a2d6f624
fix rope error when loading models with different dtypes
|
6 months ago |
AlpinDale
|
c5066558a1
add dtype to cos sin cache casting
|
6 months ago |
AlpinDale
|
6fc1ec6e9a
fix redirects and improve low level debugging
|
6 months ago |
AlpinDale
|
110a2724f4
extended -> llama3, also make rope_type in config work
|
6 months ago |
AlpinDale
|
3ab36e6b2d
feat: extended RoPE for Llama 3.1 (#543)
|
6 months ago |
AlpinDale
|
e7b1368156
feat: Phi3 support
|
6 months ago |
AlpinDale
|
fca911ee0a
vLLM Upstream Sync (#526)
|
6 months ago |
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 months ago |
AlpinDale
|
e702f587cf
feat: add batched RoPE kernels (#371)
|
9 months ago |
AlpinDale
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
10 months ago |
AlpinDale
|
ea0f57b233
feat: allow further support for non-cuda devices (#247)
|
11 months ago |
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
1 year ago |
AlpinDale
|
f013d714c0
chore: merge dev branch into main (#177)
|
1 year ago |
AlpinDale
|
2755a48d51
merge dev branch into main (#153)
|
1 year ago |
AlpinDale
|
7e8483c6d7
chore: rope refactors (#114)
|
1 year ago |
AlpinDale
|
5175605f8d
fix: yarn (#112)
|
1 year ago |
AlpinDale
|
efc6f7fbec
chore: reformats (#90)
|
1 year ago |
AlpinDale
|
bdad759503
feat: YaRN context window extension support (#67)
|
1 year ago |
AlpinDale
|
75c27d3e65
massive overhaul
|
1 year ago |