SkqLiao
|
19c824f9d0
|
change cpu-infer due to actual cpu cores on self-hosted server.
|
2025-03-20 10:10:52 +08:00 |
|
SkqLiao
|
bad334fa5b
|
fix path
|
2025-03-19 21:28:58 +08:00 |
|
SkqLiao
|
bc369b256c
|
add CI/CD for human eval score benchmarking
|
2025-03-19 21:25:21 +08:00 |
|
SkqLiao
|
c66ca65778
|
write to log
|
2025-03-15 17:10:44 +08:00 |
|
SkqLiao
|
a1891b845d
|
remove unsupprted paramters, add force think
|
2025-03-15 17:04:42 +08:00 |
|
SkqLiao
|
4e23a4c024
|
split two test
|
2025-03-15 11:32:43 +08:00 |
|
SkqLiao
|
0899b7dde6
|
remove file output est
|
2025-03-15 03:17:35 +08:00 |
|
SkqLiao
|
570c98c52d
|
remove output test
|
2025-03-15 03:17:17 +08:00 |
|
SkqLiao
|
6385308ff0
|
replace sed with awk
|
2025-03-15 03:11:26 +08:00 |
|
SkqLiao
|
9d19b7b4d4
|
fix sed
|
2025-03-15 03:03:38 +08:00 |
|
SkqLiao
|
336b5dd590
|
fix sed command
|
2025-03-15 02:55:36 +08:00 |
|
SkqLiao
|
2ed4dff85d
|
fix command typo
|
2025-03-15 02:51:03 +08:00 |
|
SkqLiao
|
f21ea700f3
|
fix term
|
2025-03-15 02:45:35 +08:00 |
|
SkqLiao
|
0be19c39e9
|
change cicd option default
|
2025-03-15 02:37:54 +08:00 |
|
SkqLiao
|
a31e09969f
|
fix typo
|
2025-03-15 02:37:08 +08:00 |
|
SkqLiao
|
129e013b41
|
rename cicd
|
2025-03-15 02:36:37 +08:00 |
|
SkqLiao
|
57cf449a97
|
fix command
|
2025-03-15 02:35:56 +08:00 |
|
SkqLiao
|
9812d57c11
|
fix typo, logging to file
|
2025-03-15 02:31:49 +08:00 |
|
SkqLiao
|
0f1684c28d
|
local chat for cicd test
|
2025-03-15 02:31:19 +08:00 |
|
SkqLiao
|
12949c8acd
|
fix default options
|
2025-03-15 01:47:14 +08:00 |
|
SkqLiao
|
bd9dc55a8d
|
fix option typos
|
2025-03-15 01:45:49 +08:00 |
|
SkqLiao
|
6c98bb6009
|
modify job name
|
2025-03-15 01:45:07 +08:00 |
|
SkqLiao
|
8c51f520dd
|
fix install issue & add test
|
2025-03-15 01:43:38 +08:00 |
|
SkqLiao
|
4e1a7630aa
|
fix cicd script
|
2025-03-14 23:13:39 +08:00 |
|
SkqLiao
|
a8d159771e
|
fix flash_attn whl path
|
2025-03-14 23:09:37 +08:00 |
|
Atream
|
b4ad815ef0
|
Merge pull request #891 from kvcache-ai/performance-optimize-gpu
use compile for gate, slight performance improvement
|
2025-03-14 20:45:24 +08:00 |
|
Atream
|
a889288fc1
|
use compile for gate, slight performance improvement
|
2025-03-14 12:43:28 +00:00 |
|
Atream
|
6c4ed59175
|
Merge pull request #886 from kvcache-ai/fix-singleton-zbx
fix-singleton
|
2025-03-14 12:18:30 +08:00 |
|
Atream
|
6f43bbe55f
|
fix-singleton
|
2025-03-14 04:16:53 +00:00 |
|
Atream
|
7f57769c23
|
Merge pull request #852 from Lander-Hatsune/main
cpuinfer: filter repeated backend instantiation
|
2025-03-14 11:45:41 +08:00 |
|
Atream
|
1c001b80aa
|
Merge pull request #880 from flappyknight/patch-1
Update install.md
|
2025-03-14 11:28:29 +08:00 |
|
jqz
|
233ac55e2a
|
Update install.md
this is a issue in your install tutorial
|
2025-03-13 17:59:24 +08:00 |
|
ZiWei Yuan
|
4f22d726a5
|
Merge pull request #847 from isxylands/fix-avx512-popcount
fix #829: support older AVX512-capable CPUs
|
2025-03-11 21:07:51 +08:00 |
|
Lander-Hatsune
|
d166fb9f6e
|
cpuinfer: filter repeated backend instantiation
|
2025-03-10 22:03:04 +08:00 |
|
liu.shen
|
26bd889ff8
|
fix #829: 兼容Intel Cascade Lake架构的CPU
|
2025-03-09 19:26:12 +08:00 |
|
Atream
|
09c043d8a6
|
Merge pull request #842 from BITcyman/fix-openai_chat_completion
[fix] thread context bug
|
2025-03-07 22:56:19 +08:00 |
|
BITcyman
|
08a8b553d6
|
[fix] thread context bug
|
2025-03-07 14:52:16 +00:00 |
|
Atream
|
7544eadd41
|
Merge pull request #840 from kvcache-ai/Atream-patch-3
release 0.2.3.post1
|
2025-03-07 22:09:09 +08:00 |
|
Atream
|
f8c1821f1d
|
Update __init__.py
|
2025-03-07 22:08:48 +08:00 |
|
Atream
|
0bc43e02bf
|
Merge pull request #839 from kvcache-ai/fix-precision-flashinfer
fix flashinfer precision
|
2025-03-07 22:08:06 +08:00 |
|
Atream
|
d453c320f1
|
fix flashinfer precision
|
2025-03-07 14:07:00 +00:00 |
|
wang jiahao
|
96d75d53df
|
Merge pull request #835 from BITcyman/fix-openai_chat_completion
[fix] support openai chat completion api
|
2025-03-07 17:22:00 +08:00 |
|
BITcyman
|
299c4dca64
|
[update] support openai chat completion api
|
2025-03-07 08:51:09 +00:00 |
|
ZiWei Yuan
|
63b1c8525b
|
Merge pull request #820 from kvcache-ai/develop-0.2.3
Develop 0.2.3 ready to release
|
2025-03-06 14:46:09 +08:00 |
|
liam
|
407e1b9ab2
|
🚑 Merge branch 'develop-0.2.3' of https://github.com/kvcache-ai/ktransformers into develop-0.2.3
|
2025-03-06 13:52:01 +08:00 |
|
Azure
|
27475cf8a5
|
fix compile
|
2025-03-06 05:34:37 +00:00 |
|
liam
|
8eeb6dd432
|
⚡ update compile option for avx512vpopcntdq
|
2025-03-06 12:18:04 +08:00 |
|
Azure
|
dd390835ca
|
Add compile condition
|
2025-03-06 03:25:39 +00:00 |
|
Azure
|
1bcfce8cad
|
Merge pull request #815 from kvcache-ai/develop-0.2.3
[fix] fix gcc compilation
|
2025-03-06 00:07:17 +08:00 |
|
Azure
|
8068018504
|
fix gcc compilation
|
2025-03-05 15:59:56 +00:00 |
|