Commit graph

940 commits

Author SHA1 Message Date
danglinfei
361cbf6329 fix local chat on npu 2025-09-26 09:30:27 +08:00
cen121212
63ec4d4b4f
Merge pull request #17 from cen121212/main-9-1-luochen
fix:迁移后修复balance_server tp=1 不开图下沉报错2
2025-09-23 11:32:34 +08:00
TOCEN
90003109fa fix:迁移后修复balance_server tp=1 不开图下沉报错2 2025-09-23 11:31:19 +08:00
cen121212
c4685d2204
Merge pull request #16 from cen121212/main-9-1-luochen
fix:迁移后修复balance_server tp=1 不开图下沉报错1
2025-09-23 11:15:29 +08:00
TOCEN
82cc131e47 fix:迁移后修复balance_server tp=1 不开图下沉报错1 2025-09-23 11:13:51 +08:00
cen121212
b19efe7a5b
Merge pull request #15 from cen121212/main-9-1-luochen
fix:迁移后修复balance_server tp=1 不开图下沉报错
2025-09-22 21:00:01 +08:00
TOCEN
7be6dfa1d6 fix:修复balance_server tp=1 不开图下沉报错 2025-09-22 20:52:07 +08:00
cen121212
1dbbf3be9f
Merge pull request #10 from RICHARDNAN/br_czn_main-9-1
revert install.sh
2025-09-11 15:41:51 +08:00
RICHARDNAN
faf86e2ff5
Update install.sh 2025-09-11 15:26:02 +08:00
cen121212
d7005e0785
Merge pull request #9 from cen121212/main-9-1-chengshaoxu
merge NPU csrc to GPU: part 6
2025-09-11 14:42:47 +08:00
Shaoxu Cheng
899e5c492c
merge NPU csrc to GPU: part 6 2025-09-11 14:40:34 +08:00
cen121212
4fd8fbe675
Merge pull request #5 from cen121212/br_whq_cmakelist_into_main
Merge CMakeLists.txt in for_arm
2025-09-11 11:12:49 +08:00
wanghanqingLYT
758e1790e0
Merge branch 'main-9-1' into br_whq_cmakelist_into_main 2025-09-11 10:22:22 +08:00
cen121212
aa11b35540
Merge pull request #2 from cen121212/br_whq_v0.2.4_into_main
merge arm branch for sgemm.cpp, tinyblas_cpu_sgemm.inc and iqk_mul_ma…
2025-09-11 09:37:50 +08:00
cen121212
cea135e56b
Merge pull request #3 from WithHades/main-9-1
Main 9 1
2025-09-11 09:36:24 +08:00
cen121212
a582b2ad7d
Merge pull request #4 from RICHARDNAN/br_czn_main-9-1
merge install.sh install_for_npu.sh setup.py
2025-09-11 09:36:03 +08:00
cen121212
0c9b3504dd
Merge pull request #7 from cen121212/main-9-1-chengshaoxu
Merge npu csrc part to ktransformers
2025-09-11 09:34:56 +08:00
cen121212
27a9da62ba
Merge pull request #8 from cen121212/main-9-1-luochen
适配npu----models/operators文件夹
2025-09-11 09:34:41 +08:00
wanghanqingLYT
f2aec8032f npu enabling for deepseekv3 model and expert.py 2025-09-09 15:35:42 +08:00
cen121212
a9a9a95b0b
适配npu-models/operators文件夹4 2025-09-08 19:43:06 +08:00
cen121212
3aee5caa77
适配npu-models/operators文件夹3 2025-09-08 19:42:41 +08:00
Shaoxu Cheng
dcabb3ca6e
merge NPU csrc to GPU: part 5 2025-09-08 19:42:33 +08:00
cen121212
ef2665a362
适配npu-models/operators文件夹2 2025-09-08 19:42:14 +08:00
Shaoxu Cheng
00f536622d
merge NPU csrc to GPU: part 4 2025-09-08 19:42:14 +08:00
Shaoxu Cheng
1d94264992
merge NPU csrc to GPU: part 3 2025-09-08 19:41:13 +08:00
Shaoxu Cheng
dea06aa77f
merge NPU csrc to GPU: part 2 2025-09-08 19:40:53 +08:00
cen121212
e0318c0fc3
适配npu-models/operators文件夹 2025-09-08 19:40:36 +08:00
Shaoxu Cheng
3125616ca2
merge NPU csrc to GPU: part 1 2025-09-08 19:40:17 +08:00
无脸男
f2a3ba0697
ktransformers 2025-09-08 17:49:18 +08:00
无脸男
cecc37841d
balance serve 2025-09-08 17:46:26 +08:00
无脸男
35369ed6e3
completions 2025-09-08 17:30:49 +08:00
wanghanqingLYT
ed566b5f23
Merge CMakeLists.txt in for_arm 2025-09-08 17:24:53 +08:00
RICHARDNAN
c89959fe1d
Update setup.py 2025-09-08 17:18:57 +08:00
无脸男
a344f2b5d4
utils 2025-09-08 17:18:07 +08:00
无脸男
76301e8e6e
utils 2025-09-08 17:07:38 +08:00
RICHARDNAN
3e700fd536
Update merge_safetensor_gguf.py 2025-09-08 15:42:06 +08:00
RICHARDNAN
125558851e
Delete serve_test.sh 2025-09-08 15:38:54 +08:00
RICHARDNAN
e0c8258b2a
Delete scripts directory 2025-09-08 15:38:30 +08:00
RICHARDNAN
82b9bbfa49
Update install_for_npu.sh 2025-09-08 15:38:05 +08:00
RICHARDNAN
ba9e964fcd
Update merge_safetensor_gguf.py 2025-09-08 15:34:30 +08:00
无脸男
3d8ff57f78
custom loader 2025-09-08 14:56:04 +08:00
无脸男
68eadd3bdc
custom gguf loader 2025-09-08 14:51:25 +08:00
无脸男
9299c25e43
optimize.py 2025-09-08 14:48:54 +08:00
无脸男
d0432ed5c4
yaml 2025-09-08 14:46:33 +08:00
wanghanqingLYT
e7e2c2bd70 merge arm branch for sgemm.cpp, tinyblas_cpu_sgemm.inc and iqk_mul_mat.inc 2025-09-08 14:11:17 +08:00
RICHARDNAN
ecdd3f383f
Delete 0.sh 2025-09-05 17:04:58 +08:00
无脸男
f940b23fee
args 2025-09-05 15:06:39 +08:00
无脸男
e99e2367c7
chat 2025-09-05 15:06:32 +08:00
无脸男
7823bac5ef
balance serve 2025-09-05 15:04:54 +08:00
无脸男
83b1ff07ab
ktransformers 2025-09-05 14:53:11 +08:00