a498720a75
[RL] Add clear_graph_opt_backend for glm4_mtp ( #7378 )
...
* add clear_grpah func
* fix spell
2026-04-15 19:44:15 +08:00
c1fb3112f8
[FDConfig] Support CLI args for quantization params and add cudagraph validation ( #7281 )
...
* refactor quant cli param
2026-04-10 14:13:42 +08:00
c29e86fc9d
[Feature] Support mtp overlap schedule ( #7001 )
2026-04-01 14:24:26 +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
33d6d2403c
[BugFix] fix bug when seq_lens_this_time is 2D ( #6613 )
2026-03-02 23:52:03 +08:00
d957ccd46d
seq_lens related tensor shape -> [max_num_seqs] ( #6535 )
2026-03-02 11:18:30 +08:00
2178f2829b
[Speculative Decoding] Support suffix decoding ( #6403 )
...
* support suffix decoding
2026-02-26 11:42:05 +08:00
5e78c1ac87
[Graph Optimization] Support CUDAGraph for P/PD mixed Batch using SOT subgraph spliting mode ( #6196 )
...
* refine comment && refine variable name
* replace comment
2026-01-29 16:29:54 +08:00
1e3c35496c
[XPU][Graph Optimization] XPU Support CUDAGraph ( #6152 )
...
* support cuda graph
2026-01-22 14:41:56 +08:00
dda27e50f5
[Graph Optimization] remove static_op_get_block_shape_and_split_kv_block from cudagraph ( #6081 )
...
* rm static_op_get_block_shape_and_split_kv_block from cudagraph
* update max_capture_shape
* fallback: zeros -> empty to avoid coverage check
* check graph_opt_config exists
* add max_capture_shape_dy2st && full_cuda_graph: false -> true in 28B vl test
* add use_cudagraph flag to control step_use_cudagraph
2026-01-20 14:05:18 +08:00
83a9ef51d7
[Others] add assert and only count the actual load in cuda_graph ( #5445 )
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
2025-12-10 11:22:54 +08:00
3707af7a4f
[Iluvatar] add vl into ci and support v1 loader ( #4774 )
2025-11-11 10:50:17 +08:00
fff5fb5e39
[Graph Optimization] Refactor default capture list ( #4617 )
...
* fix bug and refine code
* add debug count
* refine code
2025-10-28 21:31:02 +08:00
f42ed6d5f2
[Graph Optimization] Add dy_runnable and introduce cudagraph_switch_threshold for cudagraph mode switching ( #4578 )
...
* add new branch for sot
* reorder
* fix batch bug
2025-10-24 18:36:52 +08:00
dc7facaa7f
[Iluvatar GPU] fix ci error caused by rebuild_padding param and cuda graph ( #4504 )
2025-10-21 21:41:41 +08:00
775edcc09a
[Executor] Default use CUDAGraph ( #3594 )
...
* add start intercept
* Adjustment GraphOptConfig
* pre-commit
* default use cudagraph
* set default value
* default use cuda graph
* pre-commit
* fix test case bug
* disable rl
* fix moba attention
* only support gpu
* Temporarily disable PD Disaggregation
* set max_num_seqs of test case as 1
* set max_num_seqs and temperature
* fix max_num_batched_tokens bug
* close cuda graph
* success run wint2
* profile run with max_num_batched_tokens
* 1.add c++ memchecker 2.success run wint2
* updatee a800 yaml
* update docs
* 1. delete check 2. fix plas attn test case
* default use use_unique_memory_pool
* add try-except for warmup
* ban mtp, mm, rl
* fix test case mock
* fix ci bug
* fix form_model_get_output_topp0 bug
* fix ci bug
* refine deepseek ci
* refine code
* Disable PD
* fix sot yaml
2025-10-21 14:25:45 +08:00
6160145f82
[SOT] Change warnings to errors and remove fallback operations ( #4378 )
...
* Change warnings to errors and remove fallback operations
* fix unitest
* fix codestyle
2025-10-17 11:27:04 +08:00
b87e2c6184
[CUDAGraph]Add support for custom all-reduce operators under SOT mode ( #4386 )
2025-10-16 19:31:19 +08:00
aa27b03bc0
[Executor]CUDAGraph support Speculate Decode ( #3769 )
...
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 32b39620bc8351e83993834639a7ff2694294196@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
81959c7d88
[NewFeature]custom_allreduce support cudagraph recapture ( #4305 )
...
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
* custom_allreduce support cudagraph recapture
* add shut_down/restart default group
2025-09-29 15:56:54 +08:00
870364b547
[CUDAGraph]CUDA Graph support unique memory pool ( #4230 )
...
* cuda graph use unique memory pool
* fix custom device import bug
* refine code
* refine code
* refine code
2025-09-24 19:45:22 +08:00
b1b33211e8
[CUDAGraph] Support multi output buffers and merge some fixes from feature/exp_0908 ( #4062 )
...
* refine cudagraph
* refine cudagraph
* typo
* fix
* fix plugins
* fix
* update
* update
* update
2025-09-15 16:21:30 +08:00
987609c894
[BugFix] Fix image_feature 0-Size causing insert failed ( #4042 )
...
* update
* fix image_feature
2025-09-12 19:13:08 +08:00
d3e4ae3d49
[Executor] Adjust signal sending order in RL training ( #3773 )
...
* Adjust processing order
* fix bug
* fix update_parameters bug
* refine code
2025-09-10 13:24:20 +08:00
453487d5b0
[Feat] ernie4_5_vl_moe support CudaGraph ( #3226 )
...
* delete dynamic control flow for decode
* coda-style
* fix scatter/gather typos and use input stream instead default stream
* support 0-Size Tensor
* update runner and model
* using static mem address as input
* fix mem leak
* refine code
* update mm_buffer
* fix typo
* fix buffersize
* fix unk token
* refine code
* refine
* support other arch
* open cudagraph in vlci
* fix
* update
* update
* update
* fix cmd
* update
---------
Co-authored-by: aquagull <hongyuh@qq.com >
Co-authored-by: Yuanle Liu <yuanlehome@163.com >
2025-09-10 13:11:57 +08:00
205b706ef8
[Executor] Fix bug of import paddle with RLHF ( #3781 )
2025-09-02 17:32:13 +08:00
d6369b4d51
fix typos ( #3684 )
2025-09-01 17:50:17 +08:00
f677c032c0
[CudaGraph] [SOT] Support spliting static graph into piecewise graph with cuda_graph ( #3478 )
...
* support spliting static graph into piecewise graph with cuda_graph
* Update fastdeploy/model_executor/graph_optimization/cudagraph_piecewise_backend.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* fix merge conflict
* fix bug
---------
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-08-29 16:28:01 +08:00
00898603c8
[CUDAGraph]Add debug func ( #3616 )
...
* add print dot files
* refine code
2025-08-26 16:43:48 +08:00
2fa173e327
[Executor] CUDAGraph support RL training ( #3265 )
...
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
* add clear graph opt backend
* cuda graph support rl
* add branch
* 1.fix dynamic_weight_manager bug 2.add clear api for CasualLM
* open test case
* fix typo
* update mkdocs.yaml
* [Docs]Update mkdocs.yml
* update test case
* use unittest in graph test case
2025-08-25 20:59:30 +08:00
70ee910cd5
[Excutor] Change cudagraph hashkey from batch size to num_tokens ( #3454 )
2025-08-18 16:16:48 +08:00
0fb37ab7e4
update flake8 version to support pre-commit in python3.12 ( #3000 )
...
* update flake8 version to support pre-commit in python3.12
* polish code
2025-07-24 01:43:31 -07:00
95b5af24db
[SOT] Add sot warmup (NVIDIA GPU Only) ( #2929 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* add sot warmup
* fix code style
* change batch_size list
* add param to config
* rm free_list settings && set sot_warmup_sizes
* finish debug with dynamic dims by type annotations
* add profile_run guard
* rm sth useless
2025-07-22 21:36:14 +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
0262ef7eb3
custom all reduce support cuda graph ( #2938 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* Support enabling cuda graph and custom all reduce at the same time, and fix the overwritten custom all reduce flag
* rename communication_op to communication
2025-07-21 22:52:03 +08:00
25698d56d1
polish code with new pre-commit rule ( #2923 )
2025-07-19 23:19:27 +08:00
0fad10b35a
[Executor] CUDA Graph support padding batch ( #2844 )
...
* cuda graph support padding batch
* Integrate the startup parameters for the graph optimization backend and provide support for user - defined capture sizes.
* Do not insert max_num_seqs when the user specifies a capture list
* Support set graph optimization config from YAML file
* update cuda graph ci
* fix ci bug
* fix ci bug
2025-07-15 19:49:01 -07:00
e3768c5a83
[Executor] Fix bug of logger.debug ( #2778 )
2025-07-09 04:13:43 -07:00
03a74995b8
Clear dead code And supplementary notes ( #2757 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* 1.supplementary notes 2.delete dead code
* fix bug of forward meta
* Global modification of forward meta
* fix vl model_runner bug
2025-07-09 16:17:34 +08:00
92c2cfa2e7
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
684703fd72
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
GoldPancake