Yuanheng Zhao a37f82629d [Inference/SpecDec] Add Speculative Decoding Implementation (#5423) ... * fix flash decoding mask during verification * add spec-dec * add test for spec-dec * revise drafter init * remove drafter sampling * retire past kv in drafter * (trivial) rename attrs * (trivial) rename arg * revise how we enable/disable spec-dec		2024-04-10 11:07:52 +08:00
..
__init__.py	[Infer] Revise and Adapt Triton Kernels for Spec-Dec (#5401)	2024-04-10 11:07:51 +08:00
context_attn_unpad.py	Optimized the execution interval time between cuda kernels caused by view and memcopy (#5390)	2024-02-21 13:23:57 +08:00
flash_decoding.py	[Inference/SpecDec] Add Speculative Decoding Implementation (#5423)	2024-04-10 11:07:52 +08:00
fused_rotary_embedding.py	[Inference]Fused the gate and up proj in mlp，and optimized the autograd process. (#5365)	2024-02-06 19:38:25 +08:00
kvcache_copy.py	[Infer] Revise and Adapt Triton Kernels for Spec-Dec (#5401)	2024-04-10 11:07:51 +08:00
llama_act_combine_kernel.py	[devops] remove post commit ci (#5566)	2024-04-08 15:09:40 +08:00
no_pad_rotary_embedding.py	[Inference]Fused kv copy into rotary calculation (#5383)	2024-02-21 11:31:48 +08:00
qkv_matmul_kernel.py	[misc] update pre-commit and run all files (#4752)	2023-09-19 14:20:26 +08:00
rms_layernorm.py	[fix] multi graphs capture error	2024-03-11 10:49:31 +08:00
rotary_cache_copy.py	[Inference]Fused the gate and up proj in mlp，and optimized the autograd process. (#5365)	2024-02-06 19:38:25 +08:00
softmax.py	[misc] update pre-commit and run all files (#4752)	2023-09-19 14:20:26 +08:00