| .. |
|
__init__.py
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 ヶ月 前 |
|
cpu_executor.py
|
6212072245
api: support LoRA lineage and base model metadata management (#1072)
|
5 日 前 |
|
distributed_gpu_executor.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 週間 前 |
|
executor_base.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 週間 前 |
|
gpu_executor.py
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
2 週間 前 |
|
msgspec_utils.py
|
2f61644f6e
SPMD optimizations (#824)
|
1 ヶ月 前 |
|
multiproc_gpu_executor.py
|
638c08d9dc
fix: clean shutdown issues (#1047)
|
1 週間 前 |
|
multiproc_worker_utils.py
|
9a7d5514c4
feat: introduce MQAphroditeEngine (#1056)
|
1 週間 前 |
|
multiproc_xpu_executor.py
|
15cb8d5c26
xpu: support pipeline parallel (#932)
|
2 週間 前 |
|
neuron_executor.py
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
2 週間 前 |
|
openvino_executor.py
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
2 週間 前 |
|
ray_gpu_executor.py
|
4737c22ab3
fix: pass `APHRODITE_ATTENTION_BACKEND` to ray workers (#1009)
|
2 週間 前 |
|
ray_tpu_executor.py
|
6212072245
api: support LoRA lineage and base model metadata management (#1072)
|
5 日 前 |
|
ray_utils.py
|
6212072245
api: support LoRA lineage and base model metadata management (#1072)
|
5 日 前 |
|
ray_xpu_executor.py
|
673621a3d2
xpu: refactor the model runner for tensor parallelism (#910)
|
3 週間 前 |
|
tpu_executor.py
|
4b1b658855
tpu: implement multi-step scheduling (#1046)
|
1 週間 前 |
|
xpu_executor.py
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
2 週間 前 |
AlpinDale
6212072245
api: support LoRA lineage and base model metadata management (#1072)