JYChen 076ab07528 [RL] change glm rope_emb calculation (#7316) ...

* change glm rope_emb calculation

* glm without EnforceFmulRN

* fix ci

2026-04-11 18:36:28 +08:00

..

template_instantiation

【Hackathon 9th No.86】autogen MultiQueryDecoderAttention template_instantiation -part (#4383)

2025-10-16 17:08:19 +08:00

append_attention_c4_impl.cuh

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

append_attention_c8_impl.cuh

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

append_attention_c16_impl.cuh

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

append_attention_func.cuh

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

append_attention_kernel.h

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

decode_attention_func.cuh

init (#6642)

2026-03-04 21:55:31 +08:00

decoder_mla_attention_kernel.cu

【Hackathon 9th No.86】autogen MoeFastHardamardImplWrapper template_instantiation (#4592)

2025-10-30 10:28:36 +08:00

decoder_mla_attention_kernel.h

【Hackathon 9th No.86】autogen MoeFastHardamardImplWrapper template_instantiation (#4592)

2025-10-30 10:28:36 +08:00

decoder_write_cache_with_rope_impl.cuh

[RL] RoPE without fmad opt (#6901)

2026-03-24 21:19:53 +08:00

decoder_write_cache_with_rope_kernel.cu

[RL] change glm rope_emb calculation (#7316)

2026-04-11 18:36:28 +08:00

decoder_write_cache_with_rope_kernel.h

[RL] RoPE without fmad opt (#6901)

2026-03-24 21:19:53 +08:00

ds_mla_cache_kernel.cu

[Others] clean code (#6839)

2026-03-14 11:09:28 +08:00

ds_mla_cache_kernel.cuh

[Models][OP][Optimization] Support DeepSeek-v3.2 model, integrate DSA & Indexer architecture with FlashMLA/DeepGEMM (#6689)

2026-03-10 15:05:14 +08:00

encoder_write_cache_with_rope_impl.cuh

[RL] change glm rope_emb calculation (#7316)

2026-04-11 18:36:28 +08:00

encoder_write_cache_with_rope_kernel.h

[RL] RoPE without fmad opt (#6901)

2026-03-24 21:19:53 +08:00

get_block_shape_and_split_kv_block.cu

[BugFix] Fix Async D2H copy bug & flash mash atten cache V out of bound bug (#7221)

2026-04-10 11:31:51 +08:00

gqa_rope_write_cache.cu

[RL] change glm rope_emb calculation (#7316)

2026-04-11 18:36:28 +08:00

mem_util.cuh

init (#6642)

2026-03-04 21:55:31 +08:00

mla_cache_kernel.cu

[PD Disaggregation] Support PD deployment of DeepSeekv3. (#5251)

2025-12-02 14:11:50 +08:00

mla_cache_kernel.cuh

init (#6642)

2026-03-04 21:55:31 +08:00

mma_tensor_op.cuh

[LLM] First commit the llm deployment code

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

multiquery_attention_c4_impl.cuh

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

multiquery_attention_c4_kernel.h

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

multiquery_attention_c8_impl.cuh

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

multiquery_attention_c8_kernel.h

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

multiquery_attention_c16_impl.cuh

[OP][Optimization] Remove ENABLE_PREFILL template parameter in multi_query_append_attention_warp1_4_kernel (#7201)

2026-04-07 11:21:57 +08:00

multiquery_attention_c16_kernel.h

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

multiquery_decoder_attention_impl.cuh

init (#6642)

2026-03-04 21:55:31 +08:00

multiquery_decoder_attention_kernel.h

init (#6642)

2026-03-04 21:55:31 +08:00

pre_cache_len_concat.cu

[BugFix] Fix Async D2H copy bug & flash mash atten cache V out of bound bug (#7221)

2026-04-10 11:31:51 +08:00

qwen3_rope.h

[RL] RoPE without fmad opt (#6901)

2026-03-24 21:19:53 +08:00

speculate_write_cache_with_rope_impl.cuh

[RL] RoPE without fmad opt (#6901)

2026-03-24 21:19:53 +08:00

speculate_write_cache_with_rope_kernel.cu

[RL] change glm rope_emb calculation (#7316)

2026-04-11 18:36:28 +08:00

speculate_write_cache_with_rope_kernel.h

[RL] RoPE without fmad opt (#6901)

2026-03-24 21:19:53 +08:00

template_config.json

[Feature]Supports SWA based on appendattn (#6547)

2026-03-01 19:02:08 +08:00

utils.cuh

init (#6642)

2026-03-04 21:55:31 +08:00