bb48bcbaa2
Split enable_mm ( #7183 )
...
Co-authored-by: liuruian <liuruian@MacBook-Pro.local >
2026-04-08 11:25:41 +08:00
18f012457d
[OP][Optimization] Remove ENABLE_PREFILL template parameter in multi_query_append_attention_warp1_4_kernel ( #7201 )
2026-04-07 11:21:57 +08:00
2eea6fa97a
[BugFix] Fix kv cache int8 dynamic quant on flash and flash_mask backend ( #7028 )
...
* [BugFix] Fix kv cache int8 dynamic quant on flash and flash_mask backend
* add constexpr and code style clean
* add test
* fix code style
* fix test
2026-03-30 11:17:15 +08:00
a6351dea0b
[BugFix][Optimization] Replace silent failures with catchable exceptions and informative error messages ( #6533 )
...
* init
* init
* fix format
* add
* add files
* add ut
* fix some
* add ut
* add more
* add
* fix pre-commit
* fix pre-commit
* fix cover
* skip long seq
* add
* add
* fix
* remove not need
* fix set attr
* fix comments
* fix comments
* fix failed tests
---------
Co-authored-by: gongweibao <gognweibao@baidu.com >
2026-03-16 21:32:43 +08:00
9f0778f991
[Feature] Support EP prefill with num_worst_tokens ( #6574 )
...
* support num worst tokens
* support num worst tokens
* fix build error
* support num worst tokens: fix errors
* support num worst tokens: fix feild
* support num worst tokens: delete requiements
* replace permute and depermute op by pure cuda
* replace permute and depermute op by pure cuda
* fix ci
* fix op
* fix nan
* fix code style
---------
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
2026-03-11 17:09:07 +08:00
cf7934a4b2
[Speculative Decoding] Unify Spec and non-spec branch ( #6685 )
...
* optimize spec-inference architecture
* delete debug log
* optimize spec_method usage && fix unit_test
* add claude unit-test skill
* fix some ugly bug
* enhance robustness and bounds check
* unify method & spec_method to method to avoid bug
* activate CI
* fix unit test
* Unify logprobs computation for naive and speculative decoding, fix CUDA kernel
* fix logprob bug && optimize verify kernel
* fix exist_decode() judge
2026-03-10 23:58:44 -07:00
30f9f33f34
[Feature][BugFix][OP] Enhance Deterministic Inference Mode with Kernel-level Fixes and Batch-invariant BMM ( #6610 )
...
* add fa deter
* add ut
* add long sentence
* fix basic
* fix bugs
* fix adn
* fix first
* fix single
* fix single
* fix single test
* refine
* add more test
* refine comments
* add comments of bmm
* fix ci
* remove probe
* add
* remove not need
* refine tests
* fix comments and refine code
* refine code
* refine test
* refine test
* mv 4cards tests
* fix tests
* add
* fix comments
* fix cover
* fix cover
---------
Co-authored-by: gongweibao <gognweibao@baidu.com >
2026-03-09 10:27:53 +08:00
81e04bf5d1
[BugFix] fix flash attn mtp rope emb bug ( #6649 )
2026-03-04 21:19:12 +08:00
5382fb2c60
[BugFix] lazy enable_torch_proxy for cutlass ( #6523 )
...
* lazy enable_torch_proxy for cutlass
* test init_flash_attn_version
2026-03-02 10:43:58 +08:00
2d1531f3cb
dev opensource model support fa4/flashmasV2/V3 ( #6518 )
2026-02-26 17:46:05 +08:00
d937d6ebfd
check ( #6424 )
2026-02-10 15:55:17 +08:00
a8ffcaa068
fix fa4 test ( #6408 )
2026-02-10 10:57:21 +08:00
2b4748de4f
[MTP] refactor MTP pre_process ( #6358 )
2026-02-09 10:47:15 +08:00
116e2aea7a
Support Norm before Rope ( #6332 )
...
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com ”>
2026-02-05 15:28:52 +08:00
29a313a402
[Optimization] Support FA2/FA3/FA4 with attn_mask_q ( #6354 )
...
* support FA4 sm100
* flash attn backend support mask
* flash attn backend run flashmask correct
* add test for flash_attn_backend and flash_attn_func
* check
* add test for fa4
* requirements.txt add fa4 whl
* check test on sm100
* fix CI conflict
* add enable_torch_proxy for flash_mask
* lazy import fa4
* check
* fix tests import
* check test_load_mpt import
2026-02-05 14:39:00 +08:00
183b8d325a
[RL] Support GLM MTP RL Model ( #6267 )
2026-02-04 20:14:35 +08:00
12d4b4cb87
[Feature]Support reorder ids to split prefill and decodes ( #5779 )
...
* support reorder ids
* perfect code
* fix
* fix unittest
* delete code
* fix
* add python api
* delete custom op
* update algorithm
* fix swap
* support condense
* support condense
* support mtp
* delete code
* update
* update
* update
* update
* update for other platfrom
* update
* fix
* fix mtp
* fix ut
* update
* fix ut
* update ut
* fix
* fix encoder_cache
* fix ci
* fix
* fix vl
* Fix performance regression
* fix
* fix
* fix mtp
* fix index->req_id mapping
* fix ut
---------
Co-authored-by: root <root@yqlcc01-sys-rpm12rzmwjd.yqlcc01.baidu.com >
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com ”>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
2026-02-03 00:28:02 -08:00
8b05774fad
[Others] enhance deep_ep import and support mixed mode flash_mask_attn ( #6238 )
...
* support flashmaskattn mixed and enhance deepep import
* update
* fix
2026-01-28 00:02:02 +08:00
adc69c15d0
[Model Runner] Prepare token count and move FA3 initialization into the graph ( #6170 )
...
* prepare for token num and put FA3 init in graph
2026-01-26 12:16:57 +08:00
31410415db
FA3 support qwen3 ( #5441 )
2025-12-09 16:16:16 +08:00
2aea8a3a60
[Others] Remove useless code ( #5404 )
2025-12-08 13:59:46 +08:00
d436640735
[BugFix] Fix flash_attn_backend
2025-12-05 14:33:38 +08:00
43097a512a
[BugFix] [PD Disaggregation] fix v1 scheduler prefill node profile run & ipc transfer protocol ( #5132 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
* [fix] fix v1 scheduler profile run for append attention in prefill node
* [fix] skip send_signal if kv signal not inited for gpu and xpu
* [fix] extend fix to flash_attn & mla_attn
* [fix] fix v1 pd run in ipc transfer protocol
* [ci] add test for v1 pd profile run using ipc transfer protocol
* [style] fix code style check
* [style] fix code style again
* [fix] fix profile run
* [update] remove --num-gpu-blocks-override in example script
* [chore] rename forward_meta is_profiling to is_dummy_or_profile_run
2025-11-20 21:39:22 +08:00
6fa34102e8
[Others]get_block_shape_and_split_kv_block clean code ( #5123 )
2025-11-20 16:40:04 +08:00
5bf48de999
[KVCache] support unified cache backend ( #4903 )
...
* [Feature] support unified cache backend
* fix
* fix
* fix
* fix
* Update metax_model_runner.py
* fix
* update
* Update test_moba_attention_backend.py
---------
Co-authored-by: ltd0924 <luotingdan@baidu.com >
2025-11-12 14:54:52 +08:00
1b9f351d21
Support GPT-OSS-BF16 ( #4240 )
...
* [Feature] AppendAtten support sinks & HEAD_DIM=64
* fix bug
* fix bug
* fix bug
* fix bug
* [Feature] support gpt-oss
* fix bug
* add mask
* support-gpt-oss
* support-gpt-oss
* fix long seq
* support wint8
* support wint8
* support wint8
* update test
* change sliding windows init pos
---------
Co-authored-by: ming1753 <ideaminghp@163.com >
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com >
2025-10-20 14:44:58 +08:00
a751d977bc
[Optimization] Fuse get_max_len and get_kv_max_len ( #4369 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
* opt split_q_block
* fuse max_lens and max kv_len
2025-10-13 20:35:00 +08:00
a2ec2c4152
[FDConfig]Remove max_model_len in FDConfig ( #4350 )
...
* modify max_model_len
* fix unittest
* fix unittest
---------
Co-authored-by: root <root@yqlcc01-sys-rpm12rzmwjd.yqlcc01.baidu.com >
2025-10-11 14:04:17 +08:00
2e9e53ff7e
[FDConfig]Remove max_num_batched_tokens/max_num_seqs in parallel config ( #4116 )
...
* remove max_num_batched_tokens in parallel config
* remove max_num_seqs
* update test case
* fix test
* fix
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-09-17 10:43:35 +08:00
a7392a0ff9
【Inference Optimize】DeepSeek-V3-model MLA Optimize ( #3886 )
...
* support MLA chunk_size auto search & cuda_graph
2025-09-11 10:46:09 +08:00
3d0aaa5923
[Excutor] Experiment Feature-Support Prefill in cudagraph ( #3459 )
...
* Support prefill in Cudagraph
* Refactor GetBlockShapeAndSplitKVBlock Kernel V2
* Refactor GetBlockShapeAndSplitKVBlock Kernel V2.1
* Refactor GetBlockShapeAndSplitKVBlock Kernel V2.2
* Refactor GetBlockShapeAndSplitKVBlock Kernel V2.3
* Refactor GetBlockShapeAndSplitKVBlock Kernel V2.4
* Refactor GetBlockShapeAndSplitKVBlock Kernel V2.5
* Solve problem about encoder_num_blocks_x_cpu
* Add early-exit mechanism for attention kernel
* fix test case about append-attention
* Update testcode, Add annotations to related tensors
* move get_input_length_list
* solve test_code
* Add annotations about early-exit for attention kernel
* Add annotations about early-exit for attention kernel2
* solve comment
* solve mtp
---------
Co-authored-by: RAM <gstian5555@outlook.com >
2025-09-08 13:12:24 +08:00
8e1b35a09b
【Fix bug] w4afp8 的nblock固定为256，并且fa3的append attn 增加mask参数 ( #3771 )
...
* fix w4afp8
* 增加集中式配置
* codestyle
* fix fa3 append attn
2025-09-02 19:17:01 +08:00
d6369b4d51
fix typos ( #3684 )
2025-09-01 17:50:17 +08:00
e93d4cfcdd
Add with_output version AppendAttention ( #3302 )
...
* get use_output from fd_config
* add clear TODO description
* add mask_offset para to align with develop
* fix bug
* fix use_output logic
* fix sot bug
2025-08-28 17:10:18 +08:00
ad319a87cc
support fa3 rope3d ( #3622 )
2025-08-27 11:31:29 +08:00
3a15e0c53e
【Fix Bug】 修复 fa3 支持集中式bug ( #3235 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* fix fa3 集中式bug
* 增加qknorm参数
2025-08-06 16:24:27 +08:00
64d7a3194d
集中式支持fa3 ( #3112 )
2025-08-01 18:03:36 +08:00
d850660872
[Executor] Refactor GetBlockShapeAndSplitKVBlock Kernel ( #2989 )
...
* reset decoder_block_shape_q buffer
* refactor GetBlockShapeAndSplitKVBlock Kernel and cudagraph padding batch
* update decode_max_tile_size
* fix pre-commit
* update block_multihead_attn_backend
* update flas attn backend
* update MLA Attention
* update XPU Attention
* update gcu,iluvatar model runner
* Update MTP
* fix MTP bug
2025-07-31 00:09:31 +08:00
6ccc10ad47
Unify server-side and model-side Config (Part1) ( #3018 )
...
* move cache config
* fix mtp
2025-07-28 10:51:52 +08:00
332154f504
[feature] Support FA2 ( #3009 )
2025-07-25 14:09:00 +08:00
29c3292f02
support c4 attn && fix cache
2025-07-24 12:00:52 +08:00
172e69fe17
FA3 fix bug ( #2987 )
2025-07-23 19:07:43 +08:00
e51f018577
support chunk_prefill in fa3
2025-07-23 12:19:20 +08:00
48e6a0ca26
[SOT] Mark dynamic dims by type annotations ( #2771 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* [SOT] Mark dynamic dims by type annotations
* fix conflict of forward_meta
* mark more attn backend
* fix missing annotated and add env SOT_SPECIALIZED_DIM_NUMBERS
* auto infer implicit 0 dim dynamic dim
* revert manual marked dims
* revert missing update
* auto infer can use unsafe code in warmup stage
* check -> type_match
* fix codestyle
* restore blank line
* empty commit
* add need_warmup nonlocal;
* add doc for resolver
* add missing type hints
* unquote "ForwardMeta"
2025-07-22 00:23:52 -07:00
25698d56d1
polish code with new pre-commit rule ( #2923 )
2025-07-19 23:19:27 +08:00
d306944f4f
remove cum_offsets from get_block_shape_and_split_kv_block ( #2913 )
...
* remove padding_offsets from get_padding_offset.cu
* remove padding_offsets from get_padding_offset.cu
* remove padding_offsets from get_padding_offset.cu
* remove cum_offsets from get_block_shape_and_split_kv_block
* remove cum_offsets from get_block_shape_and_split_kv_block
2025-07-18 16:13:32 +08:00
d49f8fb30a
[Feature][MTP] Support cacheKV transfer in per_chunk mode ( #2890 )
...
* support chunk_prefill both normal and speculative_decoding(mtp)
* optimize pd-disaggregation config
* fix bug
2025-07-17 17:58:08 +08:00
4c7b8bc458
Simplify the Config code ( #2770 )
...
* simplify the code
* fix vl
* delete config
* fix
* perfect code
* fix ci
* fix xpu
* fix xpu
* fix server
* resolve conflict
* fix mtp
* resolve conflict
* fix xpu
* fix xpu
* fix vl
* fix log
* fix qwen moe
* fix qwen moe
* fix qwen moe
2025-07-14 19:50:05 +08:00
59071268b6
[Executor] Move forward_meta.py to fastdeploy/model_executor ( #2774 )
...
* Use PEP 563 in attention.py and fix conflict
* merge commit
* Change what was left out last time
2025-07-10 20:36:51 +08:00
fee544e808
fix ep prefill ( #2762 )
2025-07-09 14:03:05 +08:00
K11OntheBoat