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.

yuehuayingxueluo f366a5ea1f [Inference/kernel]Add Fused Rotary Embedding and KVCache Memcopy CUDA Kernel (#5418) ... * add rotary embedding kernel * add rotary_embedding_kernel * add fused rotary_emb and kvcache memcopy * add fused_rotary_emb_and_cache_kernel.cu * add fused_rotary_emb_and_memcopy * fix bugs in fused_rotary_emb_and_cache_kernel.cu * fix ci bugs * use vec memcopy and opt the gloabl memory access * fix code style * fix test_rotary_embdding_unpad.py * codes revised based on the review comments * fix bugs about include path * rm inline		9 months ago
..
kit	[workflow] fixed oom tests (#5275)	11 months ago
test_analyzer	[misc] update pre-commit and run all files (#4752)	1 year ago
test_auto_parallel	[npu] change device to accelerator api (#5239)	11 months ago
test_autochunk	[misc] update pre-commit and run all files (#4752)	1 year ago
test_booster	[fix] remove unnecessary dp_size assert (#5351)	10 months ago
test_checkpoint_io	[fsdp] impl save/load shard model/optimizer (#5357)	9 months ago
test_cluster	[misc] update pre-commit and run all files (#4752)	1 year ago
test_config	[misc] update pre-commit and run all files (#4752)	1 year ago
test_device	[misc] update pre-commit and run all files (#4752)	1 year ago
test_fx	[misc] update pre-commit and run all files (#4752)	1 year ago
test_gptq	[feature] add gptq for inference (#4754)	1 year ago
test_infer	[Inference/kernel]Add Fused Rotary Embedding and KVCache Memcopy CUDA Kernel (#5418)	9 months ago
test_lazy	[workflow] fixed oom tests (#5275)	11 months ago
test_legacy	[npu] change device to accelerator api (#5239)	11 months ago
test_moe	[moe] fix tests	10 months ago
test_optimizer	[lr-scheduler] fix load state dict and add test (#5369)	10 months ago
test_pipeline	Merge branch 'main' into sync/npu	11 months ago
test_shardformer	[hotfix] Fix ShardFormer test execution path when using sequence parallelism (#5230)	11 months ago
test_smoothquant	[inference] Add smmoothquant for llama (#4904)	1 year ago
test_tensor	[misc] update pre-commit and run all files (#4752)	1 year ago
test_utils	[feat] refactored extension module (#5298)	10 months ago
test_zero	[npu] change device to accelerator api (#5239)	11 months ago
__init__.py	…