Commit Graph

1222 Commits

Author SHA1 Message Date
ltd0924 3f535b45a2 [Feature] support prefix cache in DP (#4359)
* [Feature] support prefix cache in DP

* fix

* Update common_engine.py

* Update common_engine.py

* Update common_engine.py

* Update common_engine.py

---------

Co-authored-by: ltd0924 <luotingdan@baidu.com>
2025-10-11 10:12:12 +08:00
AIbin 533896fd63 fix paddle_peak_increase size (#4355)
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 21:31:38 +08:00
qwes5s5 6fd3e72da1 [FastDeploy Cli] Bench Command eval and throughput (#4239)
* bench command

* bench command

* bench command

* bench command

* bench command

---------

Co-authored-by: K11OntheBoat <your_email@example.com>
2025-10-10 16:17:44 +08:00
yinwei 20c7b741f4 [XPU] Support W4A8C8-TP4-300B Model (#4068)
* support w4a8

* delete ep block attn

* delete moe_topk_select

* update note

* update

* delte useless info

* update

* add some note

* fix some format

* update scale info

* add ans baseline

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-10-10 15:41:32 +08:00
RAM 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 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
AIbin 48fd5d757d Support MLA_CACHE & Fix V1_Schedule Bug (#4318)
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 MLA_CACHE & Fix V1_Schedule Bug
2025-10-09 12:11:25 +08:00
RichardWooSJTU 791b101195 revert worker process ipc signal suffix (#4323)
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
2025-09-30 03:56:41 -07:00
chen 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
xiaozude 7c919070f7 [Metax] support cutlass moe & optimize flash attention (#4208)
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
2025-09-29 11:22:43 +08:00
K11OntheBoat 2b2b645296 Fix bugs of splitwise_complete_prefilled_step IPCsignal clear (#4309)
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com”>
2025-09-29 11:21:22 +08:00
RichardWooSJTU 3740e33fea 【Feature】ResourceManagerV1 support need block num notifying (#4220)
* support need block num notifying

* adapt t2i

* fix unexpected change
2025-09-29 11:11:51 +08:00
李泳桦 70633c6641 [fix] fix gpu_caches key (#4311)
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
2025-09-28 21:32:57 +08:00
xiaolei373 1282ebe1b1 add_cli_tokenizer (#4278)
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
2025-09-28 20:47:35 +08:00
李泳桦 6265f4385f [feat] support prefix cache clearing when /clear_load_weight is called (#4008)
* [feat] support clearing prefix cache (cherry-picked from release/2.1)

* [fix] fix ipc suffix, use port instead

* [fix] fix prefix caching not enabled

* [fix] fix key/value_cache_scales indent

* [fix] fix ep group all-reduce

* [fix] fix clear/update lock not working when workers > 1

* [chore] add preemption triggered info log

* [fix] fix code style

* [fix] fix max_num_seqs config

* [fix] do not force enable_prefix_caching=False in dynamic loading

* [fix] fix ci

* Revert "[fix] fix ci"

This reverts commit 0bc6d55cc8.

* [fix] initialize available_gpu_block_num with max_gpu_block_num

* [fix] fix config splitwise_role

* [fix] fix clearing caches synchronization and add more logs

* [chore] print cache_ready_signal in log

* [fix] fix scheduler_config.splitwise_role

* [fix] fix cache_messager cache_ready_signal create=True

* [fix] stop cache messager from launching in mixed deployment
2025-09-28 19:42:53 +08:00
Lucas 59313ed7f9 [XPU] fix VL thinking mode (#4266) 2025-09-28 17:37:37 +08:00
Sunny-bot1 aa1cc09c5b fix machete pre quant (#4295) 2025-09-28 16:11:09 +08:00
K11OntheBoat 7b6cb72ab2 Fix wrong batch size of thinking_mask (#4296)
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com”>
Co-authored-by: xiegegege <46314656+xiegegege@users.noreply.github.com>
2025-09-28 14:56:42 +08:00
chenjian 3cef851468 [Bug fix] Fix bug for running ep (#4245)
* fix bug for ep

* fix bug
2025-09-28 14:56:18 +08:00
luukunn 17e00d9f5d fix reasoning_max_tokens (#4277) 2025-09-28 14:05:29 +08:00
xiaolei373 55124f8491 Add cli run batch (#4237)
* feat(log):add_request_and_response_log

* [cli] add run batch cli

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-09-26 14:27:25 +08:00
Zhong Hui 67e693b18b fix ernie vl distributed attr. (#4215)
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-09-26 14:18:49 +08:00
zhuzixuan 12a3587cca [Supplements and upgrades]Improvement of X1 parsers (#4172)
* reasoning_parser

* reasoning_parser

* reasoning_parser

* reasoning_parser

* reasoning_parser

* reasoning_parser

* reasoning_parser
2025-09-26 13:37:37 +08:00
memoryCoderC 4ec00df2b0 [Feature] add config api (#4254) 2025-09-26 11:21:02 +08:00
kxz2002 83d41d23b0 initial commit (#4248)
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
2025-09-25 21:42:05 +08:00
K11OntheBoat 4515ad21e9 Support limit thinking lengths (#4069)
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com”>
2025-09-25 19:55:56 +08:00
Yuanle Liu 0c6f1932c5 delete_moe_phase_in_parallel_config (#4264) 2025-09-25 17:14:37 +08:00
Lucas 87179cb744 [XPU] support XPU VL model inference (#4030)
* [XPU] support XPU VL model inference

* fix image op import and device check

* rebase develop

* fix perf
2025-09-25 14:34:15 +08:00
Zero Rains b433a93d9a fix the bug for prefilled_step_idx signal of cache_messager in cudagraph and PD (#4235)
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
2025-09-24 19:46:52 +08:00
RAM 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
CSWYF3634076 5ff10c8ced [Model] Qwen2.5VL support --use-cudagraph and unit testing (#4087)
* [BugFix] qwen2.5vl enable_thinking=true and image_patch_id bug fix

* [Docs]offine infer add apply_chat_template add_generation_prompt parameter

* [Model]qwen2.5VL support --use-cudagraph

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v2

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v3

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v4

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v5

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v6

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v7
2025-09-24 19:45:01 +08:00
luukunn 18f4977aec [fix]update apply_chat_template (#4137)
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
* update apply_chat_template

* fix unittest

* fix unittest

* fix

* fix

* fix unit test

* fix

* fix unit test

* add unit test
2025-09-24 18:56:32 +08:00
chen 7c1fd19f0f [OPs] MoE support wfp8afp8(channelwise) and improve per_token_quant_fp8 (#4238) 2025-09-24 16:39:51 +08:00
memoryCoderC 8b0ce8e3ab [Feature] add cli command serve (#4226) 2025-09-24 14:50:45 +08:00
ApplEOFDiscord 9566ae8827 [Bug Fix] disable prefix caching in mm model (#4167)
* add http get retry

* fix coments

* disable prefix caching in mm model

* fix unit test

---------

Co-authored-by: zhangjunjun04 <zhangjunjun04@baidu.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-09-24 14:43:46 +08:00
lizexu123 e8318b7477 [BugFix] fix qwen3-embedding model tp>1 (#4223)
* support qwen3-embedding

* fix ci bug

* fix

* fix ci bug

* fix ci bug

* fix

* fix qwen3-embedding

* fix

* fix

* fix
2025-09-24 14:13:26 +08:00
chen 3161014e49 [BugFix]fix v1 loader moe bf16, and supoort dynamic_load_weight create quant param (#4229)
* fix v1 loader moe bf16, and supoort dynamic_load_weight create quant param

* include_stop_str_in_output=False not return eos text
2025-09-24 14:12:05 +08:00
fmiao2372 f1b5392e20 [Intel HPU] Support intel hpu platform (#4161)
* [Intel HPU] Support intel hpu platform

* fix some issues

* apply precommit and move AttentionBackend_HPU

* fix format issue

* correct ops import

* fix ci issue

* update code in layers

* fix code style issue

* remove dense tp moe ep mode

* fix enc_dec_block_num

* fix rebase issue

* rename hpu to gaudi in readme

* rename ForwardMeta_HPU to HPUForwardMeta
2025-09-24 12:27:50 +08:00
Yuanle Liu b455fd39f3 register_model_class compatible with plugins (#4236)
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
2025-09-24 11:17:12 +08:00
yyssys d6e59447f5 [XPU] Enable XPU V1 mode based on environment variable (#4213)
* Enable XPU V1 mode based on environment variable
* add default param to xft_moe_fc_block_eb for latest xvllm compatibility; update run_ci_xpu to use latest xvllm
2025-09-24 10:29:48 +08:00
chen ec99474e71 [Test]add glm45_air logprob test and rollout model (#4175)
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
* add glm45_air logprob test

* add glm rollout model and pretrainedmodel for rl

* add glm rollout model and test

* check

* delete cudagraph in glm45

* add UT for glm rollout model

* revert glm UT
2025-09-23 21:06:07 +08:00
bukejiyu 62d1c48363 [v1 loader]code style (#4204)
* code style

* update
2025-09-23 19:36:00 +08:00
chen 1a6283424e Fix noaux_tc cuda Error 700 in CUDAGraph (#4174)
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
2025-09-23 18:41:33 +08:00
lizexu123 c96a535a5d [Feature] support qwen3-embedding model load (#4202)
* support qwen3-embedding

* fix ci bug

* fix

* fix ci bug

* fix ci bug

* fix
2025-09-23 00:14:35 -07:00
zhupengyang 9082f625ba [xpu] use cpu barrier (#4181) 2025-09-23 12:19:03 +08:00
yangjianfengo1 4325b737e7 【FIX】Change the name of sparse attn from moba to plas (#4006) (#4076)
* 【FIX】Change the name of sparse attn from moba to plas (#4006)

* 更新文档

* 【docs】 update readme (#4000)

* 更新文档

* update readme

* update docs

* 【FIX】Change the name of sparse attn from moba to plas (#3845)

* 更新文档

* 更新文档

* 更新文档

* 更新文档

* 修改moba为plas

* code style

* update ci

* code style

* update ci

* code style

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* fix max_num_seqs

* fix test load attn

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-09-23 10:26:40 +08:00
ltd0924 83720da79f [Feature] support clear data (#3601)
* [Feature] support clear data

* update

* fix

* fix

* fix

* fix

* fix

* fix

* fix
2025-09-23 10:20:02 +08:00
Jiang-Jia-Jun 772f0156f3 Remove useless code (#4195)
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
2025-09-22 21:18:19 +08:00
yzwu 504461b6b5 [Iluvatar GPU] Optimize attention performance and fix moe load ckpt error (#3651) 2025-09-22 21:13:59 +08:00
Zhang Yulong 5532e8a323 [FD CLI] Add bench cli (#4160)
* add bench cli

* Update test_main.py
2025-09-22 20:37:30 +08:00
chenjian 918ccdb123 [Feature] Support pd ep deployment with yiyan adapter (#4029)
* [Feature] Support mixed deployment with yiyan adapter in release2.2

* fix metrics

* add unit test

* add unit test

* add unit test

* Support pd ep deployment with yiyan adapter

* Support pd ep deployment with yiyan adapter

* refactor cache messager

* support scheduler v1 in PD

* suppport pd v1 + chunk prefill

* suppport pd v1 + chunk prefill

* add eplb

* support eplb

* support eplb

* support eplb

* support v1

* fix

* fix

* fix bug

* remove eplb support

* support prefix cache in P

* fix bug

* fix bug

* support one stop in V1

* fix bug

* fix ci

* fix ci

* fix

* fix

* fix

* fix

* fix

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-09-22 16:41:38 +08:00