AlpinDale
|
8463380a3d
update readme
|
1 year ago |
AlpinDale
|
99657d444b
fix: incorrect cc
|
1 year ago |
AlpinDale
|
ca43123a30
add github action to auto-build wheels
|
1 year ago |
AlpinDale
|
ab97237a04
separate stream events by double newlines
|
1 year ago |
AlpinDale
|
f4689eac60
align streaming output with regular output
|
1 year ago |
AlpinDale
|
d70ae67ead
bump version to 0.3
|
1 year ago |
AlpinDale
|
2976850553
Merge pull request #17 from PygmalionAI/dev
|
1 year ago |
AlpinDale
|
ff4016b00f
update throughput test
|
1 year ago |
AlpinDale
|
1ab15649ae
fix column parallelism in quantized layers
|
1 year ago |
AlpinDale
|
c70abc7522
fix the LLM class for quantization
|
1 year ago |
AlpinDale
|
2627a981dc
typo in sampler lol
|
1 year ago |
AlpinDale
|
70dbf7de03
imports in sampler
|
1 year ago |
AlpinDale
|
779148bfc3
fix missing import in llama modeling
|
1 year ago |
AlpinDale
|
2148f4be91
update requirements
|
1 year ago |
AlpinDale
|
472899e4bd
import any
|
1 year ago |
AlpinDale
|
45e72151a4
import dict
|
1 year ago |
AlpinDale
|
e8c0d863d7
update setuptools to compile new kernels
|
1 year ago |
AlpinDale
|
75c27d3e65
massive overhaul
|
1 year ago |
AlpinDale
|
c95d80da39
fix revision issues
|
1 year ago |
AlpinDale
|
0a54cd7e26
dict to list
|
1 year ago |
AlpinDale
|
280583cd29
forgot import in llama code
|
1 year ago |
AlpinDale
|
303c782c79
fix initialization code
|
1 year ago |
AlpinDale
|
798e6923f1
align CUDA kernels with original AWQ impl
|
1 year ago |
AlpinDale
|
c16e2c5545
import optional
|
1 year ago |
AlpinDale
|
0338f852be
fix incorrect attribute name
|
1 year ago |
AlpinDale
|
4cdf165ee9
fix engine args
|
1 year ago |
AlpinDale
|
d9c1d4f6e5
add awq support
|
1 year ago |
AlpinDale
|
c8c0b2f369
fix exception error for async
|
1 year ago |
AlpinDale
|
ed0f575fb7
Revert "make API key tied to env variable"
|
1 year ago |
AlpinDale
|
884470ec36
make API key tied to env variable
|
1 year ago |