Varun Sundar RabindranathandVarun Sundar Rabindranath b5241e41d9 [ Kernel ] FP8 Dynamic-Per-Token Quant Kernel (#6511) ...

Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

2024-07-18 01:38:35 +00:00

..

attention

[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)

2024-07-16 15:31:32 -07:00

cpu

[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)

2024-07-16 15:31:32 -07:00

moe

…

prepare_inputs

[Core] draft_model_runner: Implement prepare_inputs on GPU for advance_step (#6338)

2024-07-17 14:30:28 -07:00

punica

[Kernel] Add punica dimensions for Granite 3b and 8b (#5930)

2024-06-29 10:48:25 +08:00

quantization

[ Kernel ] FP8 Dynamic-Per-Token Quant Kernel (#6511)

2024-07-18 01:38:35 +00:00

activation_kernels.cu

[Model] Port over CLIPVisionModel for VLMs (#5591)

2024-06-20 11:52:09 +00:00

cache_kernels.cu

[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)

2024-07-16 15:31:32 -07:00

cache.h

[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)

2024-07-16 15:31:32 -07:00

cuda_compat.h

…

cuda_utils_kernels.cu

…

cuda_utils.h

…

custom_all_reduce_test.cu

…

custom_all_reduce.cu

…

custom_all_reduce.cuh

…

dispatch_utils.h

…

layernorm_kernels.cu

…

moe_align_block_size_kernels.cu

…

ops.h

[ Kernel ] FP8 Dynamic-Per-Token Quant Kernel (#6511)

2024-07-18 01:38:35 +00:00

pos_encoding_kernels.cu

…

reduction_utils.cuh

…

registration.h

…

torch_bindings.cpp

[ Kernel ] FP8 Dynamic-Per-Token Quant Kernel (#6511)

2024-07-18 01:38:35 +00:00