Jiang-Jia-Jun 05c670e593 [Sync] Update to latest code (#2679) ...

* [Sync] Update to latest code

* Add new code files

* Add new code files

* update code

* Try to fix build.sh

* Try to fix build.sh

* Update code

* Update requirements.txt

* Update code

---------

Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>

2025-07-03 15:43:53 +08:00

..

template_instantiation

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

append_attention_c4_impl.cuh

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

append_attention_c8_impl.cuh

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

append_attention_c16_impl.cuh

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

append_attention_func.cuh

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

append_attention_kernel.h

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

decode_attention_func.cuh

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

decode_attention_kernel.cu

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

decoder_write_cache_with_rope_impl.cuh

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

decoder_write_cache_with_rope_kernel.cu

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

decoder_write_cache_with_rope_kernel.h

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

encoder_write_cache_with_rope_impl.cuh

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

encoder_write_cache_with_rope_kernel.h

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

get_block_shape_and_split_kv_block.cu

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

gqa_rope_write_cache.cu

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

mem_util.cuh

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

mla_cache_kernel.cu

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

mla_cache_kernel.cuh

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +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

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +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

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_write_cache_with_rope_kernel.cu

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_write_cache_with_rope_kernel.h

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

utils.cuh

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00