You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Zhongkai Zhao 75af66cd81 [Hotfix] Fix model policy matching strategy in ShardFormer (#5064) ... * hotfix/Fix get model policy strategy in ShardFormer * fix bug in auto policy		1 year ago
..
kit	[Inference] Dynamic Batching Inference, online and offline (#4953)	1 year ago
test_analyzer	…
test_auto_parallel	…
test_autochunk	…
test_booster	[npu] add npu support for gemini and zero (#5067)	1 year ago
test_checkpoint_io	[gemini] gemini support extra-dp (#5043)	1 year ago
test_cluster	…
test_config	…
test_device	…
test_fx	…
test_gptq	…
test_infer	[Hotfix] Fix model policy matching strategy in ShardFormer (#5064)	1 year ago
test_infer_ops/triton	[inference] Refactor inference architecture (#5057)	1 year ago
test_lazy	…
test_legacy	[npu] add npu support for gemini and zero (#5067)	1 year ago
test_moe	[hotfix]: modify create_ep_hierarchical_group and add test (#5032)	1 year ago
test_optimizer	[test] merge old components to test to model zoo (#4945)	1 year ago
test_pipeline	…
test_shardformer	[gemini] gemini support extra-dp (#5043)	1 year ago
test_smoothquant	[inference] Add smmoothquant for llama (#4904)	1 year ago
test_tensor	…
test_utils	…
test_zero	[npu] add npu support for gemini and zero (#5067)	1 year ago
__init__.py	…