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.

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		8 months ago
..
__init__.py	[Inference]Add CUDA KVCache Kernel (#5406)	9 months ago
kernel_utils.py	[Inference/SpecDec] Add Speculative Decoding Implementation (#5423)	8 months ago
test_context_attn_unpad.py	[Inference]Move benchmark-related code to the example directory. (#5408)	9 months ago
test_decoding_attn.py	[Inference/SpecDec] Add Speculative Decoding Implementation (#5423)	8 months ago
test_fused_rotary_embedding.py	[Inference]Move benchmark-related code to the example directory. (#5408)	9 months ago
test_kvcache_copy.py	[Infer] Revise and Adapt Triton Kernels for Spec-Dec (#5401)	8 months ago
test_rmsnorm_triton.py	[Inference]Move benchmark-related code to the example directory. (#5408)	9 months ago
test_rotary_embdding_unpad.py	[Inference]Move benchmark-related code to the example directory. (#5408)	9 months ago
test_xine_copy.py	[Inference]Move benchmark-related code to the example directory. (#5408)	9 months ago