Commit Graph

22 Commits

Author SHA1 Message Date
yinwei
0df488c7bb support wint8 & wint4 (#4837)
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
2025-11-06 10:54:34 +08:00
yinwei
b4aa189483 [XPU] Support V1 Loader in Bf16 (#4746)
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
* add v1 support for bf16

* update

* update

* update

* update

* update

* update code
2025-11-01 16:13:25 +08:00
Lucas
5c6105f4a2 [XPU] bind some OPs for VL model with pybind (#4522) 2025-10-27 10:50:08 +08:00
yyssys
822dea8d5f [XPU]Moe uses a new operator (#4585)
* [XPU]Moe uses a new operator

* [XPU]Moe uses a new operator

* update response
2025-10-24 23:01:46 +08:00
zhupengyang
3a43dbf82d [XPU] merge apply_tp, ops support token_num = 0 (#4507) 2025-10-23 19:09:58 +08:00
yinwei
bf03b6fcea fix vl bug (#4485) 2025-10-20 20:13:34 +08:00
yyssys
97ee3c403a [XPU]Fix w4a8 garbled code issue (#4493) 2025-10-20 19:41:11 +08:00
yinwei
a64c0408b9 [XPU]Fix w4a8 precision bug && rollback moe algo (#4463)
* fix w4a8 precision bug

* add env

* code stype check
2025-10-17 18:27:53 +08:00
chen
b134e6afe6 [BugFix]Dev fix custom ar unstable result (#4437) 2025-10-17 11:47:16 +08:00
zhupengyang
26ff2f8683 [XPU] refine fused moe (#4219) 2025-10-16 19:04:07 +08:00
Lucas
a5063b96c8 [XPU] moe support VL 0-dim input (#4408) 2025-10-16 14:01:01 +08:00
zhupengyang
d6f775e33b [XPU] fix ep (#4393) 2025-10-15 11:41:05 +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
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
zhupengyang
9409665713 [xpu] support ep (#4067)
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
2025-09-15 13:53:11 +08:00
bukejiyu
20839abccf qwen3_moe (#3084) 2025-08-06 14:45:27 +08:00
Zero Rains
25698d56d1 polish code with new pre-commit rule (#2923) 2025-07-19 23:19:27 +08:00
Yuanle Liu
61b3997b85 refactor rl get_name_mappings_to_training (#2847)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
* refactor rl get_name_mappings_to_training

* fix tp>1

* change variable name(ffn1->up_gate_proj/ffn2->down_proj)

* change variable name(linear_weight->weight/linear_bias->bias)

* add rl names mapping for vl

* fix ernie 0.3B error

* fix develop code

* fix
2025-07-15 07:31:42 -07:00
yulangz
be21ef5047 [XPU] Supports BF16 for ERNIE-4.5-21B-A3B and ERNIE-4.5-0.3B (#2765)
* fix no quant xpu moe

* change dir of xpu moe weight only
2025-07-09 15:57:51 +08:00
Jiang-Jia-Jun
05c670e593 [Sync] Update to latest code (#2679)
* [Sync] Update to latest code

* Add new code files

* Add new code files

* update code

* Try to fix build.sh

* Try to fix build.sh

* Update code

* Update requirements.txt

* Update code

---------

Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
2025-07-03 15:43:53 +08:00
Jiang-Jia-Jun
92c2cfa2e7 Sync v2.0 version of code to github repo 2025-06-29 23:29:37 +00:00
jiangjiajun
684703fd72 [LLM] First commit the llm deployment code 2025-06-09 19:20:15 +08:00