71 Commits

Author SHA1 Message Date
hoshi-hiyouga
2bfcad2394 [model] fix kv cache (#7564) 2025-04-01 23:07:46 +08:00
Xiaosu Zhu
6b3b97c738 [misc] update liger-kernel's monkey patch (#7453)
* Update liger_kernel.py

* Update setup.py
2025-03-25 11:58:52 +08:00
hoshi-hiyouga
919415dba9 [deps] upgrade vllm to 0.8 (#7436) 2025-03-23 14:32:22 +08:00
Guo, Quan
a959c2a509 [misc] fix sglang deps (#7432)
* feat: Add transformer version requirement for sglang

* feat: add srt to sglang which is required for running sglang

Other options are srt_hip, srt_xpu, srt_npu, srt_hpu, srt_cpu, for different computation architectures.
2025-03-23 14:07:10 +08:00
hoshi-hiyouga
a306f0f5a2 [version] fix minicpmo (#7378) 2025-03-20 16:59:31 +08:00
Qiaolin Yu
a44a53ebec [inference] support sglang backend (#7278)
* Mimic SGLang offline Engine

* Add more tests and args

* Pass all current tests

* Clean Code

* fix sample_params

* clean code

* Fix Stream Chat

* change sglang from engine mode to server mode

* fix

* Fix Review Issues

* Use SGLang Built-In Utilities

* Fix test SGLang

* Some Doc Issue

* fix sglang engine

* add readme

---------

Co-authored-by: Jin Pan <jpan236@wisc.edu>
Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
2025-03-15 04:37:58 +08:00
hoshi-hiyouga
264538cb26 [misc] upgrade format to py39 (#7256) 2025-03-12 00:08:41 +08:00
hoshi-hiyouga
bf8b483186 [core] release v0.9.2 (#7254) 2025-03-11 22:42:23 +08:00
hoshi-hiyouga
71a1c1321a [config] update args (#7231)
Former-commit-id: f71a901840811bf560df671ec63a146ff99140c6
2025-03-10 23:04:43 +08:00
hoshi-hiyouga
d2f845d70d [deps] upgrade vllm (#7183)
Former-commit-id: 37678a3d64668c3b4a4bfefc054e3b9b40427c1a
2025-03-06 15:25:08 +08:00
leo-pony
b9f84900ee [npu] update cann base image and torch 2.4 (#7061)
* Update base npu container image version:The Python version required for Hugging Face Transformers is >= python3.10

* Fix the bug: arg type of INSTALL_DEEPSPEED shoud been string now.

* Update Ascend CANN, CANN-Kernel and corresponding torch and torch-npu version

* Upgrade torch-npu needs packages' version: torch==2.1.0 and torch-npu==2.4.0.post2

Former-commit-id: d6dafada58412b0c801e576ef4d8d96203f792af
2025-02-25 23:32:01 +08:00
hoshi-hiyouga
4d1791e905 [deps] upgrade vllm (#6857)
Former-commit-id: 4bd50f65a3d62528768561019fda2723d045c7fd
2025-02-08 15:02:28 +08:00
Zhangchi Feng
8f401e37f8 [model] support audio (#6701)
* support qwen2_audio

* improve code

* lint

* fix

* fix

* fix

---------

Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: 5eacb5629e4d7733cd992a63747a1335f2c6a929
2025-02-05 04:59:09 +08:00
hoshi-hiyouga
c2022431aa [misc] update license year & fix llama pro (#6814)
* fix llamapro script

* change year

Former-commit-id: d9ae594178796994d400a5f207d6499712816f89
2025-02-05 01:53:33 +08:00
hoshi-hiyouga
222423bcef [breaking] support transformers 4.48 (#6628)
Former-commit-id: f154ab175c513a4d7bb866bf2cffc34b77b50508
2025-01-31 01:36:33 +08:00
zhuHQ
c2120432db [optim] add support to APOLLO (#6617)
Former-commit-id: 5a252e5a458457adbd19da3b68a3897ad2962824
2025-01-15 00:24:56 +08:00
Zhangchi Feng
f7857c83e1 Support Inference of MiniCPM-V-2.6 and MiniCPM-o-2.6 (#6631)
* fix template name

* tiny fix

* support minicpm-o-2.6

* support inference of minicpmv

Former-commit-id: 7f3c64e853a7cdd49d02bf85e237611941ac7fa8
2025-01-14 17:34:58 +08:00
hoshi-hiyouga
28d145a066 pin vllm version to 0.6.5 (#6629)
Former-commit-id: 26097ca0adf25ebb7d9e8eec2d2cef673c6cfe88
2025-01-14 02:44:02 +08:00
Zhangchi Feng
ae32c148d1 Support new features of MiniCPM-V (#6626)
* fix template name

* tiny fix

* support minicpm-o-2.6

Former-commit-id: 53034a61c7654358f46916cbc370910fb2aeff3b
2025-01-14 00:26:19 +08:00
hiyouga
dc65ecdf09 refactor mllm param logic
Former-commit-id: b895c190945cf5d991cb4e4dea2ae73cc9c8d246
2025-01-10 15:45:48 +00:00
hiyouga
f8f05a883b fix #6482
Former-commit-id: 8577f52b4152efe6cc7a8b5f6d37b4f9ba6684e7
2024-12-30 06:03:07 +00:00
hiyouga
a897d46049 support report custom args
Former-commit-id: d41254c40a1c5cacf9377096adb27efa9bdb79ea
2024-12-21 21:42:45 +00:00
hiyouga
c1768cfb14 support batch infer in vllm
Former-commit-id: 3ef5ed3b9a44eed2f7e3ff221dfc343d0a97c0b5
2024-12-04 13:50:00 +00:00
hiyouga
1e6f96508a add vllm config
Former-commit-id: 95365f0ce4f362bde7de8b679b54b548d7055bfb
2024-11-10 21:28:18 +08:00
hiyouga
248d5daaff use pre-commit
Former-commit-id: 7cfede95df22a9ff236788f04159b6b16b8d04bb
2024-10-29 09:07:46 +00:00
hiyouga
c7efc7f2ed tiny fix
Former-commit-id: 1fe424323b212094856f423351dc2a15774d39c3
2024-10-11 23:51:54 +08:00
Johnny
3b19b6f31b Update setup.py
Former-commit-id: f85b756ffafa241304624819b7612603ad5e0ee3
2024-10-11 12:29:09 +02:00
hoshi-hiyouga
6e111eb29f Update setup.py
Former-commit-id: 4c017fe014b708d79c65eff24329b9c324399461
2024-10-07 16:26:50 +08:00
Johnny
13d73574ef Update setup.py
Former-commit-id: 73d3f93496712edace38711613e14768922d6c96
2024-10-07 10:16:53 +02:00
Johnny
1f58943b32 Update setup.py
Former-commit-id: b4de2c84b078194bb6358697fd6815d622843f58
2024-10-06 08:53:55 +02:00
hiyouga
dfff411e1a release v0.9.0 (real)
Former-commit-id: 8ff781c8ae5654680f738f69a6db9d7b95d76baf
2024-09-09 01:00:25 +08:00
hiyouga
eb5af3d90b support vllm 0.6.0
Former-commit-id: e39470ec51a9c74ad901871eb816df10e851f351
2024-09-08 02:26:20 +08:00
hiyouga
41a9c415e1 fix #5252
Former-commit-id: 73f30b4dfffb260e24f9e2332617b8ca2c249ed5
2024-09-04 03:17:54 +08:00
hiyouga
4cc8e16595 add extra requires
Former-commit-id: c47511773ae9886aae4e5ea1841866d2125abc34
2024-08-27 12:52:12 +08:00
hiyouga
59cbce1a46 add adam_mini to readme
Former-commit-id: d610c6bcf8a8ba6f4236f5d11f79571b83f4fb11
2024-08-09 20:02:03 +08:00
hiyouga
8aaf1185a5 support HQQ/EETQ #4113
Former-commit-id: b7cb51ddb394f04fe4646b2c297fc8d918c9979e
2024-06-27 00:29:42 +08:00
hiyouga
08fa707085 improve autogptq integration
Former-commit-id: d68408c7b123b8ff92014db35cac0b24b414a6f4
2024-06-26 22:11:44 +08:00
hiyouga
9fd7a410bb tiny fix about badam
Former-commit-id: 03f49267c7406e36aee35639f86e6e0383897090
2024-06-25 01:54:53 +08:00
hiyouga
bb88536166 add license
Former-commit-id: 69cfc98d7c81756a5ab6bf962240e393e449fef0
2024-06-15 17:54:33 +08:00
hiyouga
2abfad9c1f fix #4271
Former-commit-id: 03707e78d29bfcf5d395a64bb38632bdb3ff47ce
2024-06-15 05:11:33 +08:00
hiyouga
1364190a66 fix ci
Former-commit-id: 95aceebd61d195be5c980a919c12c59b56722898
2024-06-08 01:57:36 +08:00
hiyouga
31feb6e26c update readme
Former-commit-id: cc331fa2d28afe081937c50ea83d63add21d4e3a
2024-06-06 16:59:18 +08:00
hiyouga
d992f5353f fix setup
Former-commit-id: b2b80d434fcc0c3838d229098e1c21d26632204c
2024-06-06 01:39:02 +08:00
hiyouga
b74c229498 fix #4079
Former-commit-id: fda732d7f4616373844c97beff416880260f49db
2024-06-05 16:56:54 +08:00
hiyouga
d2ede9d393 fix #4022
Former-commit-id: 9541f2f1f1b7d7877eb734f051048e52003a3430
2024-06-03 18:38:36 +08:00
hiyouga
9a65820592 update readme
Former-commit-id: 440e9de66986ef7736361ce8ec3e23ce68655a56
2024-05-29 18:39:11 +08:00
hoshi-hiyouga
f4e16ae373 Merge pull request #3930 from MengqingCao/npu
Add Ascend npu doc and dependency

Former-commit-id: 7210090e4fc6531b9f6122f104875811a8798185
2024-05-29 18:33:38 +08:00
MengqingCao
e2cfd34da0 update torch-npu version
Former-commit-id: a70d7fcf2967eb30280a1fb845b39db7878f535c
2024-05-29 10:05:11 +00:00
MengqingCao
668dea9706 update cann kernels url
Former-commit-id: 23c65e9d7e8817b5815264e44cbf4a7bcb88d3d7
2024-05-29 09:53:31 +00:00
hiyouga
bceac4f554 bump vllm version to 0.4.1
Former-commit-id: a00fd39a4c2f270620711f2bfbad8d460fb4aa89
2024-05-28 21:27:27 +08:00