| .. |
|
adapter_commons
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
attention
|
5d37ec1016
suppress tpu import warning (#696)
|
vor 4 Monaten |
|
common
|
28b6397188
chore: quant config for speculative draft models (#719)
|
vor 4 Monaten |
|
distributed
|
8878e3a63f
fix: import ray under a guard (#708)
|
vor 4 Monaten |
|
endpoints
|
561588d97d
wip
|
vor 4 Monaten |
|
engine
|
28b6397188
chore: quant config for speculative draft models (#719)
|
vor 4 Monaten |
|
executor
|
008e646c7e
chore: add support for up to 2048 block size (#715)
|
vor 4 Monaten |
|
inputs
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
vor 4 Monaten |
|
kv_quant
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
vor 10 Monaten |
|
lora
|
1394008421
chore: decouple `should_modify_greedy_probs_inplace (#671)
|
vor 4 Monaten |
|
modeling
|
561588d97d
wip
|
vor 4 Monaten |
|
multimodal
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
vor 4 Monaten |
|
platforms
|
5d37ec1016
suppress tpu import warning (#696)
|
vor 4 Monaten |
|
plugins
|
f76f2a5af0
feat: add aphrodite plugin system (#705)
|
vor 4 Monaten |
|
processing
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
vor 4 Monaten |
|
prompt_adapter
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
quantization
|
04da8c33bd
Revert "chore: use the `compressed-tensors` library to avoid code reuse (#704)" (#706)
|
vor 4 Monaten |
|
server
|
ed9a6f97c1
fix: kill api server when pinging dead engine (#660)
|
vor 4 Monaten |
|
spec_decode
|
1394008421
chore: decouple `should_modify_greedy_probs_inplace (#671)
|
vor 4 Monaten |
|
task_handler
|
008e646c7e
chore: add support for up to 2048 block size (#715)
|
vor 4 Monaten |
|
transformers_utils
|
d5033e12fd
feat: implement mistral tokenizer mode (#711)
|
vor 4 Monaten |
|
triton_utils
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
_core_ext.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
_custom_ops.py
|
5d37ec1016
suppress tpu import warning (#696)
|
vor 4 Monaten |
|
_ipex_ops.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
vor 1 Jahr |
|
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
version.py
|
8e0d376f1c
ci: bump aphrodite to 0.6.1 (#722)
|
vor 4 Monaten |
AlpinDale
561588d97d
wip