AIbin c3aceb6bdc [Models][OP][Optimization] Support DeepSeek-v3.2 model, integrate DSA & Indexer architecture with FlashMLA/DeepGEMM (#6689) ...

* Support DeepSeek-v3.2 model, integrate DSA & Indexer architecture with FlashMLA/DeepGEMM

2026-03-10 15:05:14 +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

[Feature][Optimization] Qwen Support Dynamic block_wise_fp8 cache (#5486)

2025-12-12 17:10:17 +08:00

decoder_write_cache_with_rope_kernel.cu

[Feature][Optimization] Qwen Support Dynamic block_wise_fp8 cache (#5486)

2025-12-12 17:10:17 +08:00

decoder_write_cache_with_rope_kernel.h

init (#6642)

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

ds_mla_cache_kernel.cu

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

2026-03-10 15:05:14 +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

[Model Runner] Prepare token count and move FA3 initialization into the graph (#6170)

2026-01-26 12:16:57 +08:00

encoder_write_cache_with_rope_kernel.h

init (#6642)

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

get_block_shape_and_split_kv_block.cu

support dsv3 use flashmla (#6593)

2026-03-03 11:09:43 +08:00

gqa_rope_write_cache.cu

[Model Runner] Prepare token count and move FA3 initialization into the graph (#6170)

2026-01-26 12:16:57 +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

[Feature][BugFix][OP] Enhance Deterministic Inference Mode with Kernel-level Fixes and Batch-invariant BMM (#6610)

2026-03-09 10:27:53 +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

[Others] Remove useless code (#5404)

2025-12-08 13:59:46 +08:00

qwen3_rope.h

support fa3 qwen-vl rope (#5869)

2026-01-05 15:29:34 +08:00

speculate_write_cache_with_rope_impl.cuh

[Speculative Decoding] Support MTP for GLM-4.5-Air (#6047)

2026-01-16 14:35:24 +08:00

speculate_write_cache_with_rope_kernel.cu

[Speculative Decoding] Support MTP for GLM-4.5-Air (#6047)

2026-01-16 14:35:24 +08:00

speculate_write_cache_with_rope_kernel.h

support mtp rope_3d (#3791)

2025-09-04 17:18:05 +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