| .. |
|
attention
|
[Inference/Kernel] Optimize paged attention: Refactor key cache layout (#5643)
|
2024-04-25 14:24:02 +08:00 |
|
utils
|
[Inference] Delete duplicated copy_vector (#5716)
|
2024-05-14 14:35:33 +08:00 |
|
activation_kernel.cu
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
context_kv_cache_memcpy_kernel.cu
|
[Inference/Feat] Add kvcache quant support for fused_rotary_embedding_cache_copy (#5680)
|
2024-04-30 18:33:53 +08:00 |
|
convert_fp8_kernel.cu
|
[Inference/Feat] Add convert_fp8 op for fp8 test in the future (#5706)
|
2024-05-10 18:39:54 +08:00 |
|
decode_kv_cache_memcpy_kernel.cu
|
[Inference] Delete duplicated copy_vector (#5716)
|
2024-05-14 14:35:33 +08:00 |
|
flash_decoding_attention_kernel.cu
|
add paged-attetionv2: support seq length split across thread block (#5707)
|
2024-05-14 12:46:54 +08:00 |
|
fused_rotary_emb_and_cache_kernel.cu
|
[Inference] Delete duplicated copy_vector (#5716)
|
2024-05-14 14:35:33 +08:00 |
|
get_cos_and_sin_kernel.cu
|
[Inference] Delete duplicated copy_vector (#5716)
|
2024-05-14 14:35:33 +08:00 |
|
layer_norm_kernel.cu
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
moe_kernel.cu
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
multi_tensor_adam_kernel.cu
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
multi_tensor_apply.cuh
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
multi_tensor_l2norm_kernel.cu
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
multi_tensor_lamb_kernel.cu
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
multi_tensor_scale_kernel.cu
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
multi_tensor_sgd_kernel.cu
|
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
|
2024-04-24 14:17:54 +08:00 |
|
rms_layernorm_kernel.cu
|
[Inference] Remove unnecessary float4_ and rename float8_ to float8 (#5679)
|
2024-05-06 10:55:34 +08:00 |
|
scaled_masked_softmax_kernel.cu
|
[Inference] Delete duplicated copy_vector (#5716)
|
2024-05-14 14:35:33 +08:00 |
|
scaled_upper_triang_masked_softmax_kernel.cu
|
[Inference] Delete duplicated copy_vector (#5716)
|
2024-05-14 14:35:33 +08:00 |
121d7ad629