| .. |
|
__init__.py
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 months ago |
|
cpu_executor.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 weeks ago |
|
distributed_gpu_executor.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
|
executor_base.py
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 months ago |
|
gpu_executor.py
|
db96c2daa3
executor: pipe `worker_class_fn` arg in executor (#865)
|
1 month ago |
|
msgspec_utils.py
|
2f61644f6e
SPMD optimizations (#824)
|
1 month ago |
|
multiproc_gpu_executor.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
|
multiproc_worker_utils.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 weeks ago |
|
neuron_executor.py
|
008e646c7e
chore: add support for up to 2048 block size (#715)
|
3 months ago |
|
openvino_executor.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 weeks ago |
|
ray_gpu_executor.py
|
65b71f5fcc
distributed: fix issue for when nodes have multiple network interfaces (#892)
|
3 weeks ago |
|
ray_tpu_executor.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 weeks ago |
|
ray_utils.py
|
d69273bd2b
ray: better error when placement group topology is incorrect (#906)
|
3 weeks ago |
|
ray_xpu_executor.py
|
673621a3d2
xpu: refactor the model runner for tensor parallelism (#910)
|
3 weeks ago |
|
tpu_executor.py
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 months ago |
|
xpu_executor.py
|
db96c2daa3
executor: pipe `worker_class_fn` arg in executor (#865)
|
1 month ago |
AlpinDale
673621a3d2
xpu: refactor the model runner for tensor parallelism (#910)