Commit Graph

71 Commits

Author SHA1 Message Date
lzy
5300e73f8b [Others] Maintain the mtp branch temporarily. (#5446) (#5621)
Some checks failed
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
2025-12-17 06:03:25 -08:00
freeliuzc
d7d633a285 [Cherry-Pick][CI]Fix write qknorm cache bug in speculative decoding(#5491) (#5617)
* [liuzichang spend 10 dyas]fix write qknorm cache bug

* fix 'fix cachekv bug''
2025-12-17 20:08:51 +08:00
chen
5bdef760a2 [Feature][Optimization] Qwen Support Dynamic block_wise_fp8 cache (#5486) (#5536) 2025-12-15 15:53:34 +08:00
lzy
c71a44c7e5 supports mtp split_kv_attn (#5343) 2025-12-03 12:40:16 +08:00
K11OntheBoat
2e1680838f [PD Disaggregation] Support PD deployment of DeepSeekv3. (#5251)
* Support deepseekv3 cache transfer for PD deploy

* clean some log info

---------

Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com”>
2025-12-02 14:11:50 +08:00
lizhenyun01
aba4fc657f [Feature] support flash_mask_attention backend (#5134)
* [Feature] suppert flash_mask_attention backend

* fix unittest

* clean code
2025-11-28 10:12:16 +08:00
freeliuzc
2d1dade5e2 [Speculative Decoding][MTP] Support static CacheKV C8 quantization and optimize memory usage (#5155)
* support static cachekv c8 quantization in mtp mode

* optimize memory allocation
2025-11-21 15:10:13 +08:00
周周周
385fe6dade [Others] clean code (#5133) 2025-11-20 18:44:08 +08:00
周周周
6fa34102e8 [Others]get_block_shape_and_split_kv_block clean code (#5123) 2025-11-20 16:40:04 +08:00
chen
d58c1db8a0 [Feature][OP] Append Attn Support CUDA-PDL (#5072) 2025-11-17 20:47:33 +08:00
周周周
b23e684b67 revert group size 3 (#5079) 2025-11-17 18:54:13 +08:00
Sunny-bot1
8a4ddb29df Revert "[BugFix] Revert skip capture (#5023)" (#5080) 2025-11-17 16:14:55 +08:00
Sunny-bot1
249feca65a [BugFix] Revert skip capture (#5023)
Some checks failed
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
* Revert "[BugFix][Metax] Fix metax compile issue in get_block_shape_and_split_kv_block (#5000)"

This reverts commit 05da8e34c0.

* Revert "skip DtoH capture (#4988)"

This reverts commit 5b24013d46.
2025-11-13 23:52:51 -08:00
周周周
c0a4393d72 [ATTENTION] unitest (#4962) 2025-11-14 13:45:53 +08:00
carryyu
6c3d1da62f fix conflicts 2025-11-13 20:30:29 +08:00
Sunny-bot1
05da8e34c0 [BugFix][Metax] Fix metax compile issue in get_block_shape_and_split_kv_block (#5000)
* fix metax compile

* fix
2025-11-13 00:55:06 -08:00
Sunny-bot1
5b24013d46 skip DtoH capture (#4988) 2025-11-13 10:57:44 +08:00
周周周
6e01be28e0 format code (#4720)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Deploy GitHub Pages / deploy (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
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FD Image Build (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Run Accuracy Tests (push) Has been cancelled
CI Images Build / Run Stable Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
2025-11-01 19:13:50 +08:00
Zhenghai Zhang
1712e1351b 【Hackathon 9th No.86】autogen MoeFastHardamardImplWrapper template_instantiation (#4592)
* autogen MoeFastHardamardImplWrapper template_instantiation

* fix codestyle

* fix codestyle

* add impl cu files
2025-10-30 10:28:36 +08:00
RAM
86d5006a57 [Graph Optimization][Speculative Decoding] Update yaml and fix typo (#4612) 2025-10-28 11:43:26 +08:00
xiaozude
f7069b8057 [Metax] adapt DeepSeek (#4498) 2025-10-24 10:14:53 +08:00
Sunny-bot1
8718fa34b2 support static C8 (#4568)
Some checks failed
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
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FD Image Build (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Run Accuracy Tests (push) Has been cancelled
CI Images Build / Run Stable Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
2025-10-23 22:01:03 +08:00
RAM
9dc5c3e370 [Graph Optimization] Support CUDAGraph Padding + MTP (#4545)
* Support CUDAGraph Padding + MTP

* support orther write cache kernel
2025-10-23 20:57:26 +08:00
Haonan Luo
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
周周周
817210e47f [ATTN]delete code and add ffn and moe layer level test (#4440)
Some checks failed
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
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FD Image Build (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Run Accuracy Tests (push) Has been cancelled
CI Images Build / Run Stable Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
* delete code

* delete code

* delete code

* commit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit

* copmmit
2025-10-19 16:23:11 +08:00
Sunny-bot1
930f7b781c [Optimization] Put get_block_shape_and_split_kv_block in cuda graph for append attention backend (#4443)
* get block in cuda graph

* fix sot
2025-10-17 10:59:56 +08:00
Zhenghai Zhang
6adfbe07ad 【Hackathon 9th No.86】autogen MultiQueryDecoderAttention template_instantiation -part (#4383)
* split MultiQueryDecoderAttention template_instantiation

* update comment

* CI
2025-10-16 17:08:19 +08:00
Sunny-bot1
6d0cc0dd9c [Optimization] Optimize split_q_block kernel (#4367) 2025-10-15 11:28:00 +08:00
Sunny-bot1
a751d977bc [Optimization] Fuse get_max_len and get_kv_max_len (#4369)
Some checks failed
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
AIbin
f7eaca3971 【Bug Fix】mla enables tensorcore by default (#4354)
* mla tensor-core kernel is enabled by default
2025-10-10 20:45:16 +08:00
lzy
3aa04fbf21 [MTP][Cfp8]supports spec dynamic cfp8 (#4290)
* supports spec dynamic cfp8

* supports spec dynamic cfp8

---------

Co-authored-by: freeliuzc <lzc842650834@gmail.com>
2025-10-10 16:08:10 +08:00
Zhenghai Zhang
c46d5e48f8 【Hackathon 9th No.86】autogen MultiQueryAppendC8Attention template_instantiation -part (#4330)
* split MultiQueryAppendC8Attention template_instantiation

* update setup_ops.py

* fix ci

* fix bug
2025-10-10 15:07:48 +08:00
AIbin
c4ebaf8a07 【Inference Optimize】MLA Tensor-Core is enabled by default (#4335)
Some checks failed
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
2025-10-10 10:54:56 +08:00
RAM
aa27b03bc0 [Executor]CUDAGraph support Speculate Decode (#3769)
Some checks failed
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
* success run ngram

* Revert "[Code Simplification] remove cum_offsets (#3410)"

This reverts commit 32b39620bc.

* success run ngram5 tp4 42bs

* success run ngram5 tp4 42bs

* mtp draft commit

* add decorator for target model

* enable draft model in cudagraph v0.5

* revert revrt cum_offset

* enable target model in cudagraph v0.9 And clean debug code

* Revert "success run ngram"

This reverts commit 8351e83993.

* add reverted code

* enable target model in cudagraph v0.9

* solve comment

* fix bid < 0

* Enable Target Model Padding And Draft Model in cudagraph

* solve problem

* delete rebuild padding debug note

* fast compile

* Add capture list for mtp

* success run 256 tp1 mtp

* Enable Lite TP2 Bsz256

* realy enable tp2 bsz 256

* fix problem

* Solve problem for Draft model in cudagraph

* Solve comment

* replace emptytensor as zeros

* Solve comments

* Revert "fast compile"

This reverts commit 834639a7ff.

* fix bug

* fix merge bug

* fix typo

* fix bug

---------

Co-authored-by: lizexu <2694294196@qq.com>
Co-authored-by: littledgg <1658565283@qq.com>
Co-authored-by: zeroRains <linjunlu@zerorains.top>
Co-authored-by: gongshaotian <gstain5555@outlook.com>
2025-10-09 21:18:29 +08:00
Zhenghai Zhang
aa045aa84f fix typos (#4274)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Deploy GitHub Pages / deploy (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
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Run Accuracy Tests (push) Has been cancelled
CI Images Build / Run Stable Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
2025-09-27 09:25:43 +08:00
Yohanna
44010cee13 FIX] Fix CUDA error(700): 'cudaErrorIllegalAddress' in CascadeAppendWriteCacheKVQKV cache_kernel(). Continue when batch_id_per_token[token_idx] is default value -1. (#4218) 2025-09-24 14:08:49 +08:00
Yuan Xiaolan
de8638b1e9 fix dynamic Cfp8 computing error (#4119)
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-09-16 20:21:49 +08:00
AIbin
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
chen
637d96c6ae [Feature] Support zai-org/GLM-4.5-Air BF16 model (#3928)
Some checks failed
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
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Run Accuracy Tests (push) Has been cancelled
CI Images Build / Run Stable Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
* support glm45_air
2025-09-10 19:36:10 +08:00
freeliuzc
7ee100903f support rope_3d in spec mode (#4034) 2025-09-10 03:15:05 -07:00
lzy
f12159b630 del batch id per token (#3963)
* Update decoder_write_cache_with_rope_kernel.cu

del batch_id_per_token

* Update decoder_write_cache_with_rope_impl.cuh

* Update test_append_attention.py

* Update test_append_attention.py
2025-09-08 21:58:34 +08:00
co63oc
aadd6a94d8 fix typos (#3951) 2025-09-08 15:22:41 +08:00
Jundong Liu
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
lzy
af49b81ffd supports dynamic Cfp8 (#3767)
Some checks failed
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
* supports dynamic Cfp8

* add unittest
2025-09-07 20:41:29 -07:00
周周周
f6f726c773 clean code in sttantion (#3917) 2025-09-05 20:49:01 +08:00
xiaoxiaohehe001
f265a26f8b support mtp rope_3d (#3791)
* support mtp rope_3d

* Update speculate_write_cache_with_rope_kernel.cu
2025-09-04 17:18:05 +08:00
Yuan Xiaolan
fa58a9fa8f qk norm for speculate decode C16 (#3637) 2025-09-03 14:53:56 +08:00
lzy
7a521bbf62 Modify mask_offset‘s format (#3525)
* modify mask_offset in decode

* modify mask_offset unittest

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-09-02 03:05:35 -07:00
lizhenyun01
bed09ae8f8 fix mask_offset in append_attn (#3745)
Some checks failed
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 mask_offset in append_attn

* fix test
2025-08-31 15:03:16 +08:00
xiaoxiaohehe001
ad319a87cc support fa3 rope3d (#3622) 2025-08-27 11:31:29 +08:00