 AlpinDale
|
feb5840f2a
feat: async tokenization (#374)
|
9 months ago |
|
AlpinDale
|
29c241c115
fix: explicitly disallow installation on non-linux platforms (#373)
|
9 months ago |
 AlpinDale
|
97a2b26c97
fix: assertion error when use_sliding_window is present
|
9 months ago |
|
AlpinDale
|
0f6d56b07f
feat: model executor refactor (#367)
|
9 months ago |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 months ago |
|
AlpinDale
|
c41462cfcd
feat: exllamav2 quantization (#305)
|
10 months ago |
|
AlpinDale
|
c2d77b1822
chore: logging refactor (#302)
|
10 months ago |
|
AlpinDale
|
a98babfb74
fix: bnb on Turing GPUs (#299)
|
10 months ago |
|
AlpinDale
|
9810daa699
feat: INT8 KV Cache (#298)
|
10 months ago |
|
AlpinDale
|
e0c35bb353
feat: bitsandbytes and `--load-in{4,8}bit` support (#294)
|
10 months ago |
|
AlpinDale
|
705821a7fe
feat: AQLM quantization support (#293)
|
10 months ago |
|
AlpinDale
|
a1d8ab9f3e
fix: lora on quantized models (barred gguf) (#292)
|
10 months ago |
|
AlpinDale
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
10 months ago |
|
AlpinDale
|
72229a94da
feat: better marlin kernels (#285)
|
10 months ago |
|
AlpinDale
|
657aec0cbd
refactor: OpenAI endpoint (#261)
|
10 months ago |
|
AlpinDale
|
842912d022
feat: on-the-fly gguf conversion (#250)
|
11 months ago |
|
AlpinDale
|
ea0f57b233
feat: allow further support for non-cuda devices (#247)
|
11 months ago |
|
AlpinDale
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
11 months ago |
|
AlpinDale
|
31c95011a6
feat: FP8 E5M2 KV Cache (#226)
|
11 months ago |
|
AlpinDale
|
641bb0f6e9
feat: add custom allreduce kernels (#224)
|
11 months ago |
|
AlpinDale
|
26a717b49f
fix: use head_dim if available
|
11 months ago |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
11 months ago |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 months ago |
|
AlpinDale
|
15a0454172
feat: FP8 KV Cache (#185)
|
1 year ago |
|
AlpinDale
|
b9b295d74e
chore: backlogs 1 (#191)
|
1 year ago |
|
AlpinDale
|
7d91e9e0f2
feat: CUDA graphs (#172)
|
1 year ago |
|
AlpinDale
|
725be3e0de
feat: mixtral HF with expert parallelism (#167)
|
1 year ago |
|
AlpinDale
|
35e9cf707c
chore: force pt for mixtral (#164)
|
1 year ago |
|
AlpinDale
|
653da510d1
chore: rewrite InputMetadata (#143)
|
1 year ago |
|
AlpinDale
|
1334a833a4
feat: AMD ROCm support (#95)
|
1 year ago |
