Yuanheng Zhao 0f2b46a41c [kernel] Revise KVCache copy triton kernel API (#5273) ... * [kernel/fix] revise kvcache copy kernel api * fix benchmark		2024-01-16 14:41:02 +08:00
..
kernel_utils.py	[kernel] Add KV cache copy kernel during decoding (#5261)	2024-01-15 17:37:20 +08:00
test_context_attn_unpad.py	[kernel] Add flash decoding triton kernel for blocked kv cache (#5249)	2024-01-11 13:46:14 +00:00
test_decoding_attn.py	[kernel] Add flash decoding triton kernel for blocked kv cache (#5249)	2024-01-11 13:46:14 +00:00
test_kvcache_copy.py	[kernel] Revise KVCache copy triton kernel API (#5273)	2024-01-16 14:41:02 +08:00
test_layernorm_triton.py	[misc] update pre-commit and run all files (#4752)	2023-09-19 14:20:26 +08:00
test_llama_act_combine.py	[moe] merge moe into main (#4978)	2023-11-02 02:21:24 +00:00
test_rotary_embdding_unpad.py	[Inference] Kernel: no pad rotary embedding (#5252)	2024-01-11 13:46:14 +00:00
test_softmax.py	[misc] update pre-commit and run all files (#4752)	2023-09-19 14:20:26 +08:00