Commit Graph
164 Commits
Author SHA1 Message Date
wangxiyuan e88db68cf5 [Platform] platform agnostic for EngineArgs initialization (#11225)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2024-12-16 22:11:06 -08:00
Gregory Shtrasberg b63ba84832 [ROCm][bugfix] scpecilative decoding worker class (#11035)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2024-12-09 14:00:29 -08:00
wangxiyuan aea2fc38c3 [Platform] Move async output check to platform (#10768)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2024-12-09 17:24:46 +00:00
wangxiyuan 661175bc82 [platform] Add verify_quantization in platform. (#10757)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2024-11-29 15:22:21 +00:00
youkaichao eebad39f26 [torch.compile] support all attention backends (#10558)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-22 14:04:42 -08:00
youkaichaoandNick Hill a111d0151f [platforms] absorb worker cls difference into platforms folder (#10555)
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2024-11-21 21:00:32 -08:00
Mengqing Cao 9d827170a3 [Platforms] Add device_type in Platform (#10508)
Signed-off-by: MengqingCao <cmq0113@163.com>
2024-11-21 04:44:20 +00:00
youkaichao 388ee3de66 [torch.compile] limit inductor threads and lazy import quant (#10482)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-20 18:36:33 -08:00
Mengqing Cao 8c1fb50705 [Platform][Refactor] Extract func get_default_attn_backend to Platform (#10358)
Signed-off-by: Mengqing Cao <cmq0113@163.com>
2024-11-19 11:22:26 +08:00
Cyrus Leung 26a68d5d7e [CI/Build] Add test decorator for minimum GPU memory (#8925) 2024-09-29 02:50:51 +00:00
Cyrus Leung 6ffa3f314c [CI/Build] Avoid CUDA initialization (#8534) 2024-09-18 10:38:11 +00:00
youkaichao bc6e42a9b1 [hardware][rocm] allow rocm to override default env var (#7926) 2024-08-27 19:50:06 -07:00
youkaichao eed020f673 [misc] use nvml to get consistent device name (#7582) 2024-08-16 21:15:13 -07:00
youkaichao 482045ee77 [hardware][misc] introduce platform abstraction (#6080) 2024-07-02 20:12:22 -07:00