Commit Graph

96 Commits

Author SHA1 Message Date
K11OntheBoat bb48bcbaa2 Split enable_mm (#7183)
Co-authored-by: liuruian <liuruian@MacBook-Pro.local>
2026-04-08 11:25:41 +08:00
Nana 367d37b523 fix typo (#7147) 2026-04-07 16:30:32 +08:00
cmcamdy 7a2e33098f [XPU] Refactor pre process (#6993)
* [XPU] support speculate_pre_process

* merge develop

* fix codestype

* fix mtp, support cu_seqlens_q_output

* fix mtp, support cu_seqlens_q_output

* fix test

---------

Co-authored-by: lizan1999 <lizan03@baidu.com>
2026-04-01 20:29:55 +08:00
gongweibao 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
ming1753 bb925c605f [Other] Adjust GPUModelRunner to enhance compatibility (#6851) 2026-03-16 14:49:19 +08:00
cmcamdy 3543088d3e [XPU] rm stop nums (#6651)
* rm stop nums

* fix conflict

---------

Co-authored-by: Jiaxin Sui <95567040+plusNew001@users.noreply.github.com>
2026-03-12 14:05:58 +08:00
Yonghua Li 7811eeccaa [fix] resolve get_save_output_v1 socket name conflicts between multiple instances (#6758) 2026-03-11 15:02:32 +08:00
freeliuzc 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
zccjjj ae71ada6fe reduce warmup input_length for cudagragh (#6701) 2026-03-09 14:06:43 +08:00
cmcamdy 29d9cb10e9 fix tp4 dp1 (#6624) 2026-03-04 10:12:34 +08:00
zccjjj a2072fe20c [XPU] support warmup with ep & remove apply_tp_fused_op (#6289) 2026-02-28 15:40:36 +08:00
cmcamdy 13447279aa [XPU] Fix PD + MTP (#6495)
* fix pd + mtp

* fix code style

* fix PD + MTP, D get P's first token

* add anno for gpu(speculate_update)

* update draft insertv1

* fix wapper & kernel

* fix wapper

* fix code stype
2026-02-27 19:07:35 +08:00
yinwei 3cd0ffe36c Enable CudaGraph 2026-01-22 19:49:33 +08:00
yinwei 1e3c35496c [XPU][Graph Optimization] XPU Support CUDAGraph (#6152)
* support cuda graph
2026-01-22 14:41:56 +08:00
zccjjj 14a64e9b3b [XPU] change XPU EP interface from xDeepEP to paddle (#5706)
* add ENV VAR to controll low lantency buffer
2026-01-21 18:23:45 +08:00
yinwei 85d995100a Update Dummy Run To Suppport Mutil-Batch Execution (#6123) 2026-01-21 14:20:44 +08:00
ddchenhao66 3685474799 [XPU] xpu support mm prefill batch (#6072)
Co-authored-by: ddchenhao66 <dhaochen163.com>
2026-01-19 14:36:35 +08:00
guozhuangzhuang d2f1ec2b1b [XPU] fix(xpu_model_runner): reset seq_lens_encoder to 0 for decode role in PD splitwise mode (#6048)
* fix(xpu_model_runner): reset seq_lens_encoder to 0 for decode role in PD splitwise mode

- Set seq_lens_encoder to 0 when splitwise_role is 'decode' during prefill processing
- This ensures proper continuation of decoding after P generate first token in PD disaggregated architecture
- Fixes potential sequence length inconsistency in PD splitwise deployment scenarios

* format
2026-01-15 20:24:56 +08:00
cmcamdy 59d8ae0a25 [XPU] Speculate Decoding + PD, benchmark fix (#6036)
* fix mtp pd

* fix kernel

* fix code style

* fix kernel

* fix test / clear debug code

* fix test / clear debug code

* fix codestyle

* fix codestyle

* fix codestyle
2026-01-15 19:19:03 +08:00
chenjian 74d0f1c01f [Optim] Robust sync status when preempted happens (#5796)
* [Bug fix] Sync status for caching output cache

* fix

* fix

* fix bug

* fix

* fix

* support xpu

* fix

* fix

* fix

* fix

* fix

* fix ci

* fix ci

* fix xpu

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2026-01-14 12:07:33 +08:00
zhupengyang 9db48ecb34 [XPU] fix dp4 (#5946) 2026-01-09 20:36:53 +08:00
ddchenhao66 733014bf32 [XPU] Support EP4TP1 in pd disaggregation (#5860)
Co-authored-by: ddchenhao66 <dhaochen163.com>
2026-01-06 15:25:36 +08:00
cmcamdy 690d4bcdb0 [XPU] Speculative Decoding with PD (#5856)
* [XPU] Speculative Decoding with PD

* fix post process

* share kv cache sender

* support speculate decoding step system cache

* support speculate decoding step system cache

---------

Co-authored-by: root <root@gajl-bbc-onlinec-com-1512108.gajl.baidu.com>
2026-01-05 17:31:03 +08:00
Yonghua Li 5e4e6692a4 [BugFix] fix cache manager not launched in case of mtp or blockwise fp8 (#5840)
* [BugFix] fix cache manager not launched in case of mtp or blockwise fp8

* [fix] fix mtp cache in mtp.py

* [fix] fix gpu ops import

* [fix] fix mtp layer idx

* [fix] fix xpu model runner mtp cache

* [fix] fix mtp import
2026-01-04 04:35:37 -08:00
CSWYF3634076 9286403570 [Models] Add Qwen3-VL Model Support (#5763)
* support v1 loader

* remove useless code

* remove useless

* [Model] support Qwen3VL images success

* [Model] support Qwen3VL rope_3d

* [Model] support Qwen3VL remove log

* [Model] support Qwen3VL RL

* [Model] support Qwen3VL tp

* [Model] support Qwen3VL video

* [Model] support Qwen3VL fix ernievl

* [Model] support Qwen3VL fix get_image_boundaries.cc array out of bounds

* [Model] support Qwen3VL fix multi card

* [Model] support Qwen3VL file close

* [Model] support Qwen3VL fix ce

* [Model] support Qwen3VL fix unittest

* [Model] support Qwen3VL add unittest

---------

Co-authored-by: Ayakouji <yuhongh@qq.com>
2025-12-29 17:39:33 +08:00
ddchenhao66 56a9ecccb2 [XPU] xpu support ep4tp4 (#5773)
* [XPU] xpu support ep4tp4

* Add commands to check multiprocessing and fastdeploy processes

---------

Co-authored-by: ddchenhao66 <dhaochen163.com>
Co-authored-by: Jiaxin Sui <95567040+plusNew001@users.noreply.github.com>
2025-12-29 11:27:01 +08:00
qw86972190 135e47d551 [XPU]ZMQ logprob (#5628)
* [XPU]ZMQ logprob
2025-12-25 14:50:01 +08:00
ddchenhao66 4a74f5ab9b [XPU]Set top_p=0.0 by default on XPU to optimize performance (#5686)
Co-authored-by: ddchenhao66 <dhaochen163.com>
2025-12-23 11:01:01 +08:00
qw86972190 c606df59f5 [XPU]logprob bug (#5626) 2025-12-18 12:07:20 +08:00
Yonghua Li 0c8c6369ed [Feature] [PD Disaggregation] simplify configuration for pd-disaggregated deployment, and refactor post-init and usage for all ports (#5415)
* [feat] simplify configuration for pd-disaggregated deployment, and refactor post-init and usage for all ports

* [fix] fix some bugs

* [fix] fix rdma port for cache manager/messager

* [fix] temporarily cancel port availability check to see if it can pass ci test

* [feat] simplify args for multi api server

* [fix] fix dp

* [fix] fix port for xpu

* [fix] add tests for ports post processing & fix ci

* [test] fix test_multi_api_server

* [fix] fix rdma_comm_ports args for multi_api_server

* [fix] fix test_common_engine

* [fix] fix test_cache_transfer_manager

* [chore] automatically setting FD_ENABLE_MULTI_API_SERVER

* [fix] avoid api server from creating engine_args twice

* [fix] fix test_run_batch

* [fix] fix test_metrics

* [fix] fix splitwise connector init

* [test] add test_rdma_transfer and test_expert_service

* [fix] fix code syntax

* [fix] fix test_rdma_transfer and build wheel with rdma script
2025-12-17 15:50:42 +08:00
Lucas 888c4b992d [XPU] refactor of block_attn param 'pos_emb_type' (#5511) 2025-12-12 14:30:09 +08:00
cmcamdy 6cc3cb4bcf fix mtp multi batch (#5521) 2025-12-12 14:11:20 +08:00
kevin 954a145d57 [Optimization] support mm prefill batch (#5313)
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
* support mm prefill batch

* update code

* update code

* update code

* update code

* fix encoder cache bug

* update code

* update code

* fix bug

* fix paddle ocr bug

* fix xpu bug

* update code
2025-12-11 22:21:14 +08:00
lizexu123 95eab9f9ee [Feature] support stop_token_ids (#5399)
* support stop_token_ids

* fix

* delete chinese

* support both

* delete print
2025-12-09 17:49:12 +08:00
zccjjj e927c65742 [XPU] [Optimization] [EP] EP communication optimization. (#5145)
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
2025-12-05 10:03:45 +08:00
Longzhi Wang 5cd17fd662 [Models] Add forward_meta to moe models' forward function (#5138)
* [Models] Add forward_meta to moe models' forward function

* fix missing param

* fix

* fix

* fix forward_meta

* fix test and remove chunked MoE releated in config

* fix test

* fix

* fix
2025-12-04 13:26:58 +08:00
ddchenhao66 4e8096bd0d [XPU] xpu support mm prefix cache (#5356)
Co-authored-by: ddchenhao66 <dhaochen163.com>
2025-12-03 19:07:34 +08:00
qw86972190 6048ea37bd [XPU]add enable_logprob (#5279)
* [XPU]Update document

* [XPU]Update documentation

* [XPU]add enable_logprob

* Fix code style issues

* “doc”

* “docs”

* “doc”

* Fix code style via pre-commit

---------

Co-authored-by: root <root@gajl-bbc-onlinec-com-1498354.gajl.baidu.com>
2025-12-02 15:32:28 +08:00
cmcamdy 9f4977eb74 [xpu] support mtp for xpu(mix) (#5274)
* [XPU] support kernel for mtp(base)

* [XPU] support kernel for mtp(base)

* format

* format

* format

* fix gather next token

* fix step && add test

* fix

* mv pre/post process

* add adjust batch / gather next token for mtp

* fix code style

* fix mtp kenrel name

* fix mtp kernel test

* mv xpu pre/post process

* mv xpu pre/post process

* [xpu] support mtp

* fix code style
2025-12-01 11:03:14 +08:00
cmcamdy 5a67a6d960 [XPU] support kernel for mtp(base) (#4748)
* [XPU] support kernel for mtp(base)

* [XPU] support kernel for mtp(base)

* format

* format

* format

* fix gather next token

* fix step && add test

* fix

* mv pre/post process

* add adjust batch / gather next token for mtp

* fix code style

* fix mtp kenrel name

* fix mtp kernel test

* mv xpu pre/post process

* mv xpu pre/post process
2025-11-27 15:05:44 +08:00
ddchenhao66 e70e2279ce [PD Disaggregation][XPU] Add XPU support for PD disaggregation (#5113)
* [XPU] xpu support PD disaggregation

* [XPU] fix the issue of cache KV transfer process startup failure on non-zero XPU cards

* [XPU] xpu support PD disaggregation in v1 scheduler

---------

Co-authored-by: ddchenhao66 <dhaochen163.com>
2025-11-21 14:09:01 +08:00
ltd0924 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
周周周 876e4a8935 remove input_ids from ForwardMeta (#4793)
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
2025-11-05 11:55:51 +08:00
zhupengyang 2fd254e5b7 support ep+tp at op layer (#4688) 2025-11-05 11:15:57 +08:00
ddchenhao66 bffa08b74b [XPU] fix thinking bug where output only contains reasoning_content (#4761)
Co-authored-by: ddchenhao66 <dhaochen163.com>
2025-11-04 14:32:35 +08:00
ddchenhao66 3cbca75cc8 [XPU] xpu support neox style ROPE (#4719)
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
Co-authored-by: ddchenhao66 <dhaochen163.com>
2025-10-31 18:14:25 +08:00
kxz2002 a2870ed4a9 [Feature] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668)
* parser register name unify

* change ernie_x1 to ernie-x1

* change ernie4_5_vl to ernie-45-vl

* fix unit test
2025-10-31 10:45:27 +08:00
Lucas 8f40dfa9bf [XPU] fix pos_emb_type bug (#4638) 2025-10-29 17:14:32 +08:00
Lucas 0a0c74e717 [XPU] Support PaddleOCR-VL model for XPU (#4529)
* [XPU] support PaddleOCR-VL in XPU

* [XPU] fix PaddleOCR-VL pos_emb_type
2025-10-28 20:35:04 +08:00
ming1753 e4e3cede7f [Feature] Support Paddle-OCR (#4396)
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
* init

* update code

* fix code style & disable thinking

* adapt for common_engine.update_mm_requests_chunk_size

* use 3d rope

* use flash_attn_unpadded

* opt siglip

* update to be compatible with the latest codebase

* fix typo

* optim OCR performance

* fix bug

* fix bug

* fix bug

* fix bug

* normlize name

* modify xpu rope

* revert logger

* fix bug

* fix bug

* fix bug

* support default_v1

* optim performance

* fix bug

---------

Co-authored-by: root <root@szzj-acg-tge1-fdda9.szzj.baidu.com>
Co-authored-by: zhangyue66 <zhangyue66@baidu.com>
2025-10-24 23:34:30 +08:00