 齐保元
|
754e0442ae
|
[cpu] remove verbose print
|
2025-11-14 19:02:10 +08:00 |
|
|
齐保元
|
c188ff8872
|
Merge remote-tracking branch 'origin/main' into qby_dev/cpu_support
|
2025-11-14 18:56:46 +08:00 |
|
|
齐保元
|
8bac9a12ac
|
[cpu] fix comment
|
2025-11-14 18:52:38 +08:00 |
|
|
齐保元
|
ac149f6ea9
|
[cpu worker] yaml update
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
齐保元
|
8ee1d73d02
|
[cpu worker] file move
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
a4e8327797
|
adjust the doc
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
30dd7aad34
|
Debug and Update doc
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
14d8c3d95c
|
Make Example Easier To Use
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
c1a41bde05
|
rename util further rename imports
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
17e2119d2c
|
rename util
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
c10cbbd2ea
|
add data download instructions
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
7b9fa7708a
|
modify code based on review suggestions
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
a42dba230d
|
Revert "Revert "Update run script to include initialization sleep time and support for loading prompts from a .pt file.""
This reverts commit 5f3f53a39d.
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
dfe92f7d86
|
Revert "Update run script to include initialization sleep time and support for loading prompts from a .pt file."
This reverts commit c18fc40f10.
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:29 +08:00 |
|
|
tzhouam
|
86b8669494
|
Squash 7 commits: 36ada0478a 0ef1fefd45 519c140d20 c18fc40f10 5f3f53a39d da385277a2 edefcc244b
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
tzhouam
|
b5136c2e0d
|
remove text output for audio output
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
tzhouam
|
13dfb56a68
|
Refactor end-to-end inference script and enhance argument parsing. Added support for loading prompts from a .pt file, introduced new command-line arguments for initialization and output handling, and improved error handling for prompt loading. Removed deprecated files related to previous implementations.
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
tzhouam
|
6c6ff9f27c
|
Enhance error handling and logging in pipeline and stage processing. Added detailed logging for prompt loading failures, file writing issues, and stage shutdown processes. Introduced a new logging utility for orchestrator metrics and streamlined stats handling in the PipelinedOmniLLM class.
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
tzhouam
|
b8b82347d3
|
debug ar model runner
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
tzhouam
|
62b0e81795
|
Port changes from feat/multi-request-stream (vs main)
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
齐保元
|
8f7b102108
|
[fix] support loading model from local path
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
齐保元
|
5c038ae553
|
[feature] cpu worker support
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
齐保元
|
8b30818f2e
|
[feature] cpu worker support
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-14 18:44:28 +08:00 |
|
|
Gao Han
|
a089dd4c4e
|
Merge pull request #51 from tzhouam/feat/multi-request-stream-new
[Feature] Multi Request Stream for Sync Mode
|
2025-11-13 10:14:27 +08:00 |
|
|
tzhouam
|
8f6280f4f6
|
adjust the doc
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-12 15:51:56 +08:00 |
|
|
tzhouam
|
26fcae5def
|
Debug and Update doc
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-11 14:49:45 +08:00 |
|
|
tzhouam
|
c12bd006bc
|
Make Example Easier To Use
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-11 11:56:08 +08:00 |
|
|
tzhouam
|
bc69d8e931
|
rename util further rename imports
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-11 10:57:15 +08:00 |
|
|
tzhouam
|
12cc2cd245
|
rename util
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-11 10:55:57 +08:00 |
|
|
tzhouam
|
b943abb22f
|
add data download instructions
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-11 10:49:53 +08:00 |
|
|
tzhouam
|
edae58b137
|
modify code based on review suggestions
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-11 10:03:26 +08:00 |
|
|
tzhouam
|
5052bfa0b9
|
Merge branch 'feat/multi-request-stream-new' of https://github.com/tzhouam/vllm-omni into feat/multi-request-stream-new
|
2025-11-10 16:43:11 +08:00 |
|
|
tzhouam
|
c83d223e91
|
Squash 7 commits: 36ada0478a 0ef1fefd45 519c140d20 c18fc40f10 5f3f53a39d da385277a2 edefcc244b
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-10 16:42:58 +08:00 |
|
|
tzhouam
|
edefcc244b
|
Merge branch 'feat/multi-request-stream-new' of https://github.com/tzhouam/vllm-omni into feat/multi-request-stream-new
|
2025-11-10 16:37:49 +08:00 |
|
|
tzhouam
|
da385277a2
|
Revert "Revert "Update run script to include initialization sleep time and support for loading prompts from a .pt file.""
This reverts commit 5f3f53a39d.
|
2025-11-10 16:37:37 +08:00 |
|
|
tzhouam
|
5f3f53a39d
|
Revert "Update run script to include initialization sleep time and support for loading prompts from a .pt file."
This reverts commit c18fc40f10.
|
2025-11-10 16:36:55 +08:00 |
|
|
tzhouam
|
c18fc40f10
|
Update run script to include initialization sleep time and support for loading prompts from a .pt file.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-10 16:36:00 +08:00 |
|
|
Isotr0py
|
f1d8a00772
|
Merge pull request #52 from vllm-project/dev_qby
[fix] Add support for loading model from a local path
|
2025-11-10 16:03:57 +08:00 |
|
|
tzhouam
|
519c140d20
|
Update run script to include initialization sleep time and support for loading prompts from a .pt file.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-10 15:47:28 +08:00 |
|
|
tzhouam
|
0ef1fefd45
|
add prompt file
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-10 15:44:44 +08:00 |
|
|
tzhouam
|
36ada0478a
|
add back the sleep time for the stage init to avoid single card conflict
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-10 15:07:01 +08:00 |
|
|
tzhouam
|
08aef1f964
|
remove text output for audio output
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2025-11-10 14:41:44 +08:00 |
|
|
tzhouam
|
8e8783d78a
|
Refactor end-to-end inference script and enhance argument parsing. Added support for loading prompts from a .pt file, introduced new command-line arguments for initialization and output handling, and improved error handling for prompt loading. Removed deprecated files related to previous implementations.
|
2025-11-10 11:58:47 +08:00 |
|
|
齐保元
|
d7618b1be4
|
[fix] support loading model from local path
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
|
2025-11-09 04:37:19 +08:00 |
|
|
tzhouam
|
c5631ca753
|
Enhance error handling and logging in pipeline and stage processing. Added detailed logging for prompt loading failures, file writing issues, and stage shutdown processes. Introduced a new logging utility for orchestrator metrics and streamlined stats handling in the PipelinedOmniLLM class.
|
2025-11-07 18:05:00 +08:00 |
|
|
tzhouam
|
3c2ad1bf12
|
debug ar model runner
|
2025-11-07 16:25:48 +08:00 |
|
|
tzhouam
|
6a7a27801b
|
Port changes from feat/multi-request-stream (vs main)
|
2025-11-07 15:48:47 +08:00 |
|
|
Hongsheng Liu
|
86841b69e9
|
Merge pull request #48 from Gaohan123/refractor_v2
[Refractor] Dependency refractored to vLLM v0.11.0
|
2025-11-07 15:47:53 +13:00 |
|
|
Gaohan123
|
e5adae0a07
|
fix other reviews
Signed-off-by: Gaohan123 <gaohan19@huawei.com>
|
2025-11-06 19:25:55 +08:00 |
|
|
Hongsheng Liu
|
5cc8ab06db
|
Merge pull request #47 from Gaohan123/refractor
[Bugfix] fix huggingface download problem for spk_dict.pt
|
2025-11-06 16:03:31 +13:00 |
|