 yzwu
|
8789329457
|
[Iluvatar] Support wi4a16 group_gemm (#7078)
|
2026-03-30 19:03:51 +08:00 |
|
|
yzwu
|
901b38c936
|
[Iluvatar] Optimize decode group_gemm and Support cuda graph for ernie (#6803)
|
2026-03-12 19:21:17 +08:00 |
|
|
yzwu
|
67388ce2f3
|
[Iluvatar][CI] Replace ci in ernie-300B-4layer with ernie-21b. (#6747)
|
2026-03-10 17:25:52 +08:00 |
|
|
yzwu
|
81acdb62bd
|
[Iluvatar][CI] Do not specify FD_LOG_DIR (#6665)
|
2026-03-06 11:54:44 +08:00 |
|
|
yzwu
|
3345641f4e
|
[Iluvatar][CI] fix the dim error of seq_lens_encoder and seq_lens_decoder (#6637)
|
2026-03-04 14:00:40 +08:00 |
|
|
yzwu
|
6674131b0b
|
[Iluvatar] Support CudaGraph and optimize flash_attn_unpadded and fused_neox_rope_embedding (#6553)
|
2026-03-02 14:07:17 +08:00 |
|
|
Yuqiang Ge
|
1f931e05cd
|
[CI] Add retry logic for pip install in iluvatar CI script (#6500)
|
2026-02-25 16:01:41 +08:00 |
|
|
yzwu
|
60e75ea8e8
|
[Iluvatar][CI] Fix cannot import get_stop (#6165)
|
2026-02-10 16:57:23 +08:00 |
|
|
yzwu
|
837ddca273
|
[Iluvartar][CI] Fix the error max_tokens_per_expert referenced before assignment (#6083)
|
2026-01-21 16:01:29 +08:00 |
|
|
yzwu
|
29898372e9
|
[Iluvatar] remove CUDA_VISIBLE_DEVICE in run_ci_iluvatar.sh (#5916)
|
2026-01-07 14:10:47 +08:00 |
|
|
yzwu
|
7b6cc11952
|
[Iluvatar] Fix FD launch error when specifing CUDA_VISBLE_DEVICE (#5735)
|
2025-12-26 14:01:27 +08:00 |
|
|
Jiaxin Sui
|
8fc789bb3f
|
[iluvatar][CI] refactor iluvatar_ci (#5588)
* refactor iluvatar_ci
* refactor iluvatar_ci
* refactor iluvatar_ci
* refactor iluvatar_ci
* refactor iluvatar_ci
* refactor iluvatar_ci
* refactor iluvatar_ci
* refactor iluvatar_ci
* refactor iluvatar_ci
* Update Docker image tag in iluvatar_test workflow
* Update default Docker image version in workflow
* Update iluvatar_test.yml
* Update default Docker image in workflow config
* Update model path in run_ernie300B_4layer.py
* Update model path in offline inference check
* Add model_data directory and copy model files
Create model_data directory and copy necessary files.
* Update run_ernie_vl_28B.py
* Update run_ernie300B_4layer.py
* Update paddlepaddle installation method in script
* Change wget command to include proxy option
* Modify paddle package installation in CI script
Updated installation commands for paddle packages.
* Update paddlepaddle and paddle-iluvatar-gpu versions
* Delete .github/workflows/ci_iluvatar.yml
* Rename workflow from ILUVATAR Test to ILUVATAR-CI
* Update installation commands for paddlepaddle and iluvatar
|
2025-12-25 15:10:34 +08:00 |
|
|
yzwu
|
ac013803f3
|
[Iluvatar] Support V1_KVCACHE_SCHEDULER and paddleocr-vl rope mode (#5555)
|
2025-12-18 02:14:25 -08:00 |
|
|
yzwu
|
3707af7a4f
|
[Iluvatar] add vl into ci and support v1 loader (#4774)
|
2025-11-11 10:50:17 +08:00 |
|
|
yzwu
|
504461b6b5
|
[Iluvatar GPU] Optimize attention performance and fix moe load ckpt error (#3651)
|
2025-09-22 21:13:59 +08:00 |
|
|
YUNSHEN XIE
|
3a6058e445
|
Add stable ci (#3460)
* add stable ci
* fix
* update
* fix
* rename tests dir;fix stable ci bug
* add timeout limit
* update
|
2025-08-20 08:57:17 +08:00 |
|
|
yzwu
|
fbdd6b0663
|
[Iluvatar GPU] Optimze attention and moe performance (#3234)
|
2025-08-08 10:51:24 +08:00 |
|
|
liddk1121
|
17c5d3a241
|
[Iluvatar GPU] Add CI scripts (#2876)
|
2025-07-21 09:44:42 +08:00 |
|