| .. |
|
attention
|
f6250c5516
move dockerfiles to root; fix cpu build
|
7 months ago |
|
common
|
e8b7f53321
allow prompt token IDs in the logits processor api
|
7 months ago |
|
distributed
|
5b0c11d190
support pipeline parallel pynccl groups
|
7 months ago |
|
endpoints
|
e8b7f53321
allow prompt token IDs in the logits processor api
|
7 months ago |
|
engine
|
5b0c11d190
support pipeline parallel pynccl groups
|
7 months ago |
|
executor
|
5b0c11d190
support pipeline parallel pynccl groups
|
7 months ago |
|
kv_quant
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
1 year ago |
|
lora
|
5b0c11d190
support pipeline parallel pynccl groups
|
7 months ago |
|
modeling
|
7d0884de9a
fix mistral v0.3 weight loading
|
7 months ago |
|
processing
|
5b0c11d190
support pipeline parallel pynccl groups
|
7 months ago |
|
quantization
|
e8b7f53321
allow prompt token IDs in the logits processor api
|
7 months ago |
|
spec_decode
|
5b0c11d190
support pipeline parallel pynccl groups
|
7 months ago |
|
task_handler
|
5b0c11d190
support pipeline parallel pynccl groups
|
7 months ago |
|
transformers_utils
|
60e74e92fd
add rope_scaling arg
|
7 months ago |
|
__init__.py
|
be8154a8a0
feat: proper embeddings API with e5-mistral-7b support
|
7 months ago |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
1 year ago |
AlpinDale
7d0884de9a
fix mistral v0.3 weight loading