Commit Graph

1094 Commits

Author SHA1 Message Date
RICHARDNAN
376e9d674f Add RANK and LOCAL_WORLD_SIZE environment variables
Added environment variables for rank and local world size.
2025-10-24 15:17:33 +08:00
cen121212
fce8d8a03f Merge pull request #27 from RICHARDNAN/patch-1
Update supported NPU
2025-10-24 15:11:18 +08:00
RICHARDNAN
0787ba97ee Update supported NPU 2025-10-24 15:08:30 +08:00
Jianwei Dong
d7ab3b41b7 Merge pull request #1530 from kvcache-ai/kt-kernel
update kt-kernel
2025-10-24 14:33:10 +08:00
ovowei
da4c68c7a0 update kt-kernel 2025-10-24 14:32:45 +08:00
cen121212
0d6f105761 Merge pull request #26 from RICHARDNAN/csx-main-fix
fix ktransformers local_chat
2025-10-24 14:04:39 +08:00
RICHARDNAN
573c603656 Update DeepseekR1_tutorial_zh_for_Ascend_NPU.md 2025-10-24 11:59:53 +08:00
RICHARDNAN
930a3c35bc Merge branch 'csx-main-fix' of https://github.com/RICHARDNAN/ktransformers into csx-main-fix 2025-10-24 11:57:03 +08:00
RICHARDNAN
ca4b3a9011 新增npu readme 2025-10-24 11:56:22 +08:00
RICHARDNAN
3a966d6fb1 Merge branch 'csx-main-fix' into csx-main-fix 2025-10-23 17:55:03 +08:00
RICHARDNAN
5ce1381edd fix transformers local_chat 2025-10-23 17:51:19 +08:00
TOCEN
15dddc20c0 处理检视意见 2025-10-23 11:28:42 +08:00
Jianwei Dong
5180fe8714 Merge pull request #1527 from kvcache-ai/kt-kernel
fix kt-kernel
2025-10-22 18:15:17 +08:00
ovowei
28d8663374 fix 2025-10-22 18:14:34 +08:00
cen121212
df15a40720 Merge pull request #24 from RICHARDNAN/czn_fix_gpu
Czn fix gpu
2025-10-21 22:02:02 +08:00
TOCEN
bd0ae78d9d fix:npu运行报错修复 2025-10-21 21:54:59 +08:00
RICHARDNAN
8a681876e4 fix gpu 2025-10-21 19:32:06 +08:00
RICHARDNAN
d228c1b107 Merge branch 'csx-main-fix' into czn_fix_gpu 2025-10-21 18:56:52 +08:00
RICHARDNAN
61e2807c48 Update sched_rpc.py 2025-10-21 18:40:06 +08:00
RICHARDNAN
6392f079fc Update model_runner.py 2025-10-21 18:36:03 +08:00
RICHARDNAN
296645edce fix gpu 2025-10-21 17:48:04 +08:00
root
a40ecaa64a 合并fix some bugs 2025-10-20 12:34:36 +00:00
Atream
d44800c1cf Merge pull request #1523 from kvcache-ai/kt-kernel
add kt-kernel
2025-10-12 13:15:51 +08:00
Atream
4c5fcf9774 add kt-kernel 2025-10-12 05:13:00 +00:00
Atream
a064cc8525 Merge pull request #1522 from kvcache-ai/Atream-patch-9
Update README with Citation link
2025-10-10 19:12:52 +08:00
Atream
8ef6111ae0 Update README with Citation link 2025-10-10 19:12:31 +08:00
Atream
44d426500a Merge pull request #1521 from kvcache-ai/Atream-patch-8
Add citation section to README
2025-10-10 19:00:12 +08:00
Atream
1e48eab7d5 Add citation section to README
Added citation section with reference to KTransformers paper.
2025-10-10 18:59:29 +08:00
Atream
d38bcc8875 Merge pull request #1520 from kvcache-ai/Atream-patch-7
Add SGLang Integration to README.md
2025-10-10 18:50:40 +08:00
Atream
e93abc93ec Add SGLang Integration to README.md 2025-10-10 18:50:05 +08:00
cen121212
1d2a4d5140 Merge pull request #22 from cen121212/main-9-1
fix ktransformers
2025-10-10 10:43:19 +08:00
cen121212
d8c4090cbd Merge pull request #21 from WithHades/main-9-28
fix ktransformers
2025-10-10 10:42:06 +08:00
无脸男
39df926f93 max new token 2025-10-10 10:40:54 +08:00
cen121212
70cee18709 Merge pull request #20 from cen121212/main-9-1
Main 9 1
2025-09-29 17:31:40 +08:00
TOCEN
582738a711 fix: 合并最新main, 解决冲突 2025-09-29 17:30:40 +08:00
WithHades
113d5a1c0d fix ktransformers
Signed-off-by: WithHades <244036962@qq.com>
2025-09-28 18:01:21 +08:00
cen121212
56b6b54b59 Merge pull request #19 from cen121212/main-9-1-luochen
fix:适配balance_server tp和图下沉特性
2025-09-28 10:45:05 +08:00
cen121212
417acb4563 Merge pull request #18 from amote-i/main-9-1-dang
fix local chat on npu
2025-09-28 10:44:16 +08:00
TOCEN
cdf588faa3 fix:适配balance_server tp和图下沉特性 2025-09-26 17:18:24 +08:00
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
Jianwei Dong
8ff3966173 Merge pull request #1505 from kvcache-ai/support-qwen3next
fix qwen3next bug
2025-09-16 21:29:33 +08:00
djw
d9c75cb5aa Merge branch 'support-qwen3next' of https://github.com/kvcache-ai/ktransformers into support-qwen3next 2025-09-16 13:26:37 +00:00
djw
0437660e62 fix bug 2025-09-16 13:21:58 +00:00
Jianwei Dong
880daa7fde Merge pull request #1500 from kvcache-ai/support-qwen3next
Support qwen3next
2025-09-12 21:59:47 +08:00