 UnicornChan
|
be81269e38
|
Merge pull request #71 from Azure-Tang/main
[fix] Fix qlen > chunk_size mask is none error
|
2024-09-02 14:51:05 +08:00 |
|
|
Azure
|
c55de02f7b
|
fix qlen > 1000 mask is none error
|
2024-09-02 02:58:10 +00:00 |
|
|
UnicornChan
|
022b893819
|
Merge pull request #67 from UnicornChan/main
[fix] fix bugs about Qwen2-57B, install requirement, DockerFile
v0.1.4
|
2024-08-30 17:57:49 +08:00 |
|
|
chenxl
|
49cce0c437
|
[fix] bugs about Qwen57B, install requirement, Dockerfile
|
2024-08-30 09:51:32 +00:00 |
|
|
UnicornChan
|
351698c3b5
|
Merge pull request #64 from eltociear/patch-1
docs: update long_context_introduction.md
|
2024-08-30 09:03:47 +08:00 |
|
|
chenxl
|
c80490a95e
|
[fix] some bugs while package in github action
|
2024-08-29 19:40:03 +00:00 |
|
|
Ikko Eltociear Ashimine
|
e961adde15
|
docs: update long_context_introduction.md
accuary -> accuracy
|
2024-08-30 03:34:39 +09:00 |
|
|
UnicornChan
|
f536a7085f
|
Merge pull request #62 from Azure-Tang/main
[Fix] Fix problem that ktransformers cannot offload whole layer in cpu
|
2024-08-29 23:40:21 +08:00 |
|
|
TangJingqi
|
8747c099f2
|
update yaml example; update version idx; update docker file
|
2024-08-29 22:39:20 +08:00 |
|
|
TangJingqi
|
6735beb5b6
|
Fix cannot offload whole layer in cpu
|
2024-08-29 19:10:14 +08:00 |
|
|
Atream
|
35d7aed207
|
Merge pull request #60 from sammcj/patch-1
fix(docs): fix broken link
|
2024-08-29 19:01:16 +08:00 |
|
|
Sam
|
0b57627bb9
|
fix(docs): fix broken link
|
2024-08-29 20:00:55 +10:00 |
|
|
Azure
|
1dcb8dae5b
|
Merge pull request #58 from Azure-Tang/main
[fix] Fix readme datas
|
2024-08-29 14:39:58 +08:00 |
|
|
TangJingqi
|
440d827e7c
|
update readme
|
2024-08-29 12:04:56 +08:00 |
|
|
TangJingqi
|
abd4214b56
|
fix readme; adjust param
|
2024-08-29 10:40:08 +08:00 |
|
|
UnicornChan
|
233bbb8c55
|
Merge pull request #57 from UnicornChan/develop-0.1.3
[feature] release 0.1.3
v0.1.3
|
2024-08-29 01:57:34 +08:00 |
|
|
chenxl
|
4d1d561d28
|
[feature] release 0.1.3
|
2024-08-28 16:11:43 +00:00 |
|
|
UnicornChan
|
67f8b370c3
|
Merge pull request #56 from hyx1999/patch-1
Update README.md
|
2024-08-28 14:30:38 +08:00 |
|
|
_HYX_
|
ea1143e54e
|
Update README.md
Set the reminder to set CUDA_HOME and CUDA_PATH in the README to the "Quick Start" section under "Install CUDA".
|
2024-08-28 12:15:38 +08:00 |
|
|
UnicornChan
|
0f054fe4ff
|
Merge pull request #52 from UnicornChan/fix-bug-load-config
Fix: None for load config
|
2024-08-22 23:54:17 +08:00 |
|
|
chenxl
|
b9f0819a86
|
None for load config
|
2024-08-22 15:52:25 +00:00 |
|
|
UnicornChan
|
1f85db3d73
|
Merge pull request #51 from molamooo/fix-f16-dequantize-device
[fix] f16 dequantize device ignored
|
2024-08-22 16:31:45 +08:00 |
|
|
molamooo
|
29f4151ebc
|
[fix] f16 dequantize device ignored
|
2024-08-22 15:10:06 +08:00 |
|
|
UnicornChan
|
cbc47d0b68
|
Merge pull request #48 from Azure-Tang/main
[fix] Fix bugs about static cache and server param;
|
2024-08-21 23:24:46 +08:00 |
|
|
TangJingqi
|
170b7a6001
|
fix server don't accept yaml path as param; fix server static cache device problem
|
2024-08-21 14:19:43 +08:00 |
|
|
Azure
|
4358722891
|
Merge pull request #41 from Azure-Tang/main
Update README
|
2024-08-16 15:27:01 +08:00 |
|
|
TangJingqi
|
4a0f1cbbfa
|
Update readme
|
2024-08-16 15:22:16 +08:00 |
|
|
Azure
|
f681eb4a0f
|
Merge branch 'kvcache-ai:main' into main
|
2024-08-16 15:21:41 +08:00 |
|
|
Azure
|
b25ad4ec32
|
Merge pull request #39 from Azure-Tang/develop-0.1.2
[fix] fix broken link in tutorial.
|
2024-08-16 11:29:11 +08:00 |
|
|
TangJingqi
|
4f87756c2e
|
fix broken link
|
2024-08-16 11:10:30 +08:00 |
|
|
TangJingqi
|
7199699d78
|
Fix the broken link
|
2024-08-16 11:00:06 +08:00 |
|
|
Azure
|
e81fc482ff
|
update README
|
2024-08-15 16:59:26 +00:00 |
|
|
Azure
|
6bcec86fa0
|
update README
|
2024-08-15 16:54:31 +00:00 |
|
|
UnicornChan
|
77a34c289c
|
Merge pull request #36 from kvcache-ai/develop-0.1.2
Release v0.1.2
v0.1.2
|
2024-08-15 20:59:50 +08:00 |
|
|
UnicornChan
|
395cd3e786
|
Merge pull request #35 from Azure-Tang/develop-0.1.2
[update] Update readme; Add tutorial
|
2024-08-15 20:56:22 +08:00 |
|
|
TangJingqi
|
de3faaf55d
|
Update readme; add pipeline tutorial; add detailed inject tutorial
|
2024-08-15 20:42:54 +08:00 |
|
|
UnicornChan
|
c9bf79299b
|
Merge pull request #34 from Azure-Tang/develop-0.1.2
[fix] format classes and files name
|
2024-08-15 11:28:19 +08:00 |
|
|
TangJingqi
|
c47205dce9
|
fix name
|
2024-08-15 11:25:12 +08:00 |
|
|
TangJingqi
|
67043b4b5c
|
[fix] format classes and files name
|
2024-08-15 10:44:59 +08:00 |
|
|
chenxl
|
1db4a67dca
|
[feature] add github action for pre compile
|
2024-08-14 16:54:50 +00:00 |
|
|
Atream
|
412055d450
|
[feature] experts can be injected using CPUInfer
[fix] fix ktransformers interface when use new CUDAGraphRunner
[fix] fix YAML and optimize logic, the top rule has the highest priority
|
2024-08-14 16:10:54 +08:00 |
|
|
UnicornChan
|
80815dbc50
|
Merge pull request #30 from BITcyman/feature-lc-dequantize_q2k_q3k_gpu
[feature] support q2_k & q3_k dequantize on gpu
|
2024-08-12 21:02:32 +08:00 |
|
|
BITcyman
|
7c4cb520bd
|
[feature] support q2_k & q3_k dequantize on gpu
|
2024-08-12 12:53:12 +00:00 |
|
|
chenxl
|
650c368c18
|
Merge remote-tracking branch 'upstream/main' into develop-0.1.2
|
2024-08-12 12:31:49 +00:00 |
|
|
UnicornChan
|
44f57270c9
|
Merge pull request #29 from kvcache-ai/fix]-fix-linux-mutex
Update task_queue.h
|
2024-08-12 20:14:04 +08:00 |
|
|
Atream
|
3c675af61a
|
Update task_queue.h
|
2024-08-12 20:06:19 +08:00 |
|
|
chenxl
|
f5f79f5c0e
|
[ADD] support multi-gpu qlen>1 q5_k
|
2024-08-12 11:41:26 +00:00 |
|
|
UnicornChan
|
f293803156
|
Merge pull request #27 from chenht2022/develop-0.1.2
[Feature] towards 0.1.2
|
2024-08-09 17:57:27 +08:00 |
|
|
UnicornChan
|
cb7f8e7817
|
Merge pull request #26 from kvcache-ai/windows
[fix] linux and windows can all find CPUInfer in current Directory
|
2024-08-09 17:57:00 +08:00 |
|
|
chenxl
|
782a17e4e6
|
[feature] add bat for windows, update readme
|
2024-08-09 09:39:42 +00:00 |
|