Commit Graph

769 Commits

Author SHA1 Message Date
qiyuxinlin
ecc01cda17 update norm cpu kernel 2025-05-14 09:49:35 +00:00
qiyuxinlin
64742bec83 update torch MLA kernel 2025-05-14 09:45:12 +00:00
qiyuxinlin
e8e83308a9 fix flashinfer float_workspace_buffer small 2025-05-14 09:33:52 +00:00
wang jiahao
02948bc1b8 Merge pull request #1289 from kvcache-ai/update-default-config
update default config
2025-05-13 20:23:25 +08:00
qiyuxinlin
697444905a update default config 2025-05-13 12:20:21 +00:00
wang jiahao
8456222852 Merge pull request #1276 from kvcache-ai/support_load_safetensor
support safetensor load, delete architectures argument
2025-05-12 11:10:26 +08:00
qiyuxinlin
c6aa379de2 support safetensor load, delete architectures argument 2025-05-09 10:38:29 +00:00
Atream
30eab48a75 Merge pull request #799 from aubreyli/cpu_offloading
Restore CPU offloading capability
2025-05-09 00:38:54 -06:00
Atream
8025def197 Merge pull request #1246 from aubreyli/GenerationMixin
modeling_deepseek_v3: fix GenerationMixin warning
2025-05-09 00:35:15 -06:00
Atream
900a7f7c3e Merge pull request #1271 from kvcache-ai/fix-AMX
fix AMX
2025-05-07 05:12:38 -06:00
Atream
b22cded890 fix AMX 2025-05-07 19:12:19 +08:00
Yaochen Han
3f14e311cb Merge pull request #1247 from aubreyli/_get_logits_warper
ktransformers/utils: fix _get_logits_warper error
2025-05-07 15:22:35 +08:00
Aubrey Li
b3a1fcf471 ktransformers/utils: fix _get_logits_warper error 2025-05-01 08:13:09 +08:00
Aubrey Li
def1ec7683 modeling_deepseek_v3: fix GenerationMixin warning
Fix GenerationMixin warning introduced by upgrading transformers to 4.51.3.
2025-05-01 07:48:15 +08:00
Atream
7530491f5b Merge pull request #1244 from kvcache-ai/update-custom-flashinfer
update-custom-flashinfer
2025-04-30 04:46:19 -06:00
Atream
753075728c update-custom-flashinfer 2025-04-30 10:45:25 +00:00
Atream
a4bd6818ed Merge pull request #1241 from kvcache-ai/fix-cache-lens
fix-cache-lens
2025-04-29 21:38:12 -06:00
Atream
7adb7281f4 fix-cache-lens 2025-04-30 03:37:43 +00:00
wang jiahao
8ba7e5d4b8 Merge pull request #1227 from kvcache-ai/change-yaml
change inject yaml
2025-04-29 16:10:37 +08:00
qiyuxinlin
48dfbc8f9f change inject yaml 2025-04-29 08:09:39 +00:00
ZiWei Yuan
2a224b256e Merge pull request #1225 from kvcache-ai/fix_typo_main
 update ignore
2025-04-29 13:26:02 +08:00
liam Yuan
0e8a36770a update ignore 2025-04-29 13:24:14 +08:00
ZiWei Yuan
c519747f3c Merge pull request #1224 from kvcache-ai/fix_typo_main
 fix typo
2025-04-29 13:22:27 +08:00
liam Yuan
2762012039 fix typo 2025-04-29 13:20:03 +08:00
Atream
ab26e7d7db Merge pull request #1223 from kvcache-ai/fix-client
fix-client
2025-04-28 22:35:04 -06:00
Atream
0f7a3e5fea fix-client 2025-04-29 12:34:20 +08:00
Atream
cc94a02ab5 Merge pull request #1222 from kvcache-ai/fix-compile
Fix compile
2025-04-28 22:13:09 -06:00
Atream
08035a7cda Update requirements-local_chat.txt 2025-04-29 12:12:35 +08:00
Atream
fd9876049d Update pyproject.toml 2025-04-29 12:11:11 +08:00
Atream
9d6e09efa6 Merge pull request #1221 from kvcache-ai/Atream-patch-5
Update AMX.md
2025-04-28 21:14:10 -06:00
Atream
28948aacc9 Update AMX.md 2025-04-29 11:12:51 +08:00
Atream
bee6291dc2 Merge pull request #1220 from kvcache-ai/fix-hopper-flashinfer
fix-hopper-flashinfer
2025-04-28 21:07:34 -06:00
Atream
b0318fc01c fix-hopper-flashinfer 2025-04-29 11:06:34 +08:00
Atream
b703cc9c3d Merge pull request #1219 from kvcache-ai/Atream-patch-4
Update AMX.md
2025-04-28 21:04:12 -06:00
Atream
14efb15593 Update AMX.md 2025-04-29 11:03:59 +08:00
Atream
38333cf129 Merge pull request #1218 from kvcache-ai/clean-up
clean-up
2025-04-28 20:36:25 -06:00
Atream
192746cf93 clean-up 2025-04-29 10:32:42 +08:00
Atream
e4538bc013 Merge pull request #1217 from kvcache-ai/Atream-patch-3
Update AMX.md
2025-04-28 20:31:03 -06:00
Atream
073ce601e0 Update AMX.md 2025-04-29 10:29:51 +08:00
Atream
2bcdf10fbb Merge pull request #1216 from kvcache-ai/Atream-patch-2
Update version info in __init__.py
2025-04-28 19:58:56 -06:00
Atream
e8b2bf4f7b Update version info in __init__.py 2025-04-29 09:58:40 +08:00
Atream
5599fef98f Merge pull request #1215 from kvcache-ai/Atream-patch-1
Update Qwen3 date
2025-04-28 19:43:29 -06:00
Atream
7ebf82a492 Update Qwen3 date 2025-04-29 09:43:13 +08:00
wang jiahao
f27e4850f1 Merge pull request #1212 from kvcache-ai/support-amx-qwen
update AMX readme
2025-04-29 07:09:53 +08:00
qiyuxinlin
e70db18b63 update AMX readme 2025-04-28 23:08:38 +00:00
qiyuxinlin
2e905c8bd4 update AMX readme 2025-04-28 23:03:32 +00:00
wang jiahao
d7811a4f32 Merge pull request #1211 from kvcache-ai/support-amx-qwen
Support amx qwen
v0.3
2025-04-29 06:44:48 +08:00
qiyuxinlin
a3ba63665a update readme 2025-04-28 22:38:41 +00:00
qiyuxinlin
89823ccb1f update readme 2025-04-28 22:34:47 +00:00
qiyuxinlin
e7763a4b59 update readme 2025-04-28 22:32:35 +00:00