apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
8224b215256738c2273f833b51e896bb7c3cfbf3
FastDeploy/custom_ops/gpu_ops/append_attn
History
Jundong Liu 1e4968e810
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details
[Excutor] Fixed the issue of CUDA graph execution failure caused by different branches during decoding (#3223) 
* 彻底解决解码切块问题

* update C8 and C4 kernel

* fix problem

* fix with pre-commit

* retain branch for mtp
2025-08-09 07:37:19 +08:00
..
template_instantiation
support qk norm (#3145)
2025-08-05 16:46:14 +08:00
append_attention_c4_impl.cuh
[Excutor] Fixed the issue of CUDA graph execution failure caused by different branches during decoding (#3223)
2025-08-09 07:37:19 +08:00
append_attention_c8_impl.cuh
[Excutor] Fixed the issue of CUDA graph execution failure caused by different branches during decoding (#3223)
2025-08-09 07:37:19 +08:00
append_attention_c16_impl.cuh
[Excutor] Fixed the issue of CUDA graph execution failure caused by different branches during decoding (#3223)
2025-08-09 07:37:19 +08:00
append_attention_func.cuh
[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880)
2025-07-17 18:41:31 +08:00
append_attention_kernel.h
[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880)
2025-07-17 18:41:31 +08:00
decode_attention_func.cuh
[Sync] Update to latest code (#2679)
2025-07-03 15:43:53 +08:00
decode_attention_kernel.cu
[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880)
2025-07-17 18:41:31 +08:00
decoder_write_cache_with_rope_impl.cuh
[Bugfix] Fix model accuracy in some ops (#3231)
2025-08-08 17:30:37 +08:00
decoder_write_cache_with_rope_kernel.cu
[Bugfix] Fix model accuracy in some ops (#3231)
2025-08-08 17:30:37 +08:00
decoder_write_cache_with_rope_kernel.h
support qk norm (#3145)
2025-08-05 16:46:14 +08:00
encoder_write_cache_with_rope_impl.cuh
[Bugfix] Fix model accuracy in some ops (#3231)
2025-08-08 17:30:37 +08:00
encoder_write_cache_with_rope_kernel.h
support qk norm (#3145)
2025-08-05 16:46:14 +08:00
get_block_shape_and_split_kv_block.cu
[Executor] Refactor GetBlockShapeAndSplitKVBlock Kernel (#2989)
2025-07-31 00:09:31 +08:00
gqa_rope_write_cache.cu
fix c4 prompt_cache
2025-07-28 14:31:37 +08:00
mem_util.cuh
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
mla_cache_kernel.cu
[Feature] DeepseekV3 use pd_build_static_op (#2948)
2025-07-22 15:03:41 +08:00
mla_cache_kernel.cuh
[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880)
2025-07-17 18:41:31 +08:00
mma_tensor_op.cuh
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
multi_head_latent_attention_kernel.h
[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880)
2025-07-17 18:41:31 +08:00
pre_cache_len_concat.cu
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
speculate_write_cache_with_rope_impl.cuh
support c4 attn && fix cache
2025-07-24 12:00:52 +08:00
speculate_write_cache_with_rope_kernel.cu
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
speculate_write_cache_with_rope_kernel.h
polish code with new pre-commit rule (#2923)
2025-07-19 23:19:27 +08:00
utils.cuh
[Bugfix] Fix model accuracy in some ops (#3231)
2025-08-08 17:30:37 +08:00