exllama(v2): fix exllamav1, add exllamav2 (#1384)

* fix(exllama): fix exllama deps with anaconda

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(exllamav2): add exllamav2 backend

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2023-12-05 08:15:37 +01:00 committed by GitHub
parent 563c5b7ea0
commit 2b2d6673ff
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
13 changed files with 683 additions and 11 deletions

View file

@ -33,6 +33,7 @@ dependencies:
- mpmath==1.3.0
- networkx==3.1
- ninja==1.11.1
- protobuf==4.24.4
- nvidia-cublas-cu12==12.1.3.1
- nvidia-cuda-cupti-cu12==12.1.105
- nvidia-cuda-nvrtc-cu12==12.1.105
@ -45,11 +46,11 @@ dependencies:
- nvidia-nccl-cu12==2.18.1
- nvidia-nvjitlink-cu12==12.2.140
- nvidia-nvtx-cu12==12.1.105
- protobuf==4.24.4
- safetensors==0.3.2
- sentencepiece==0.1.99
- sympy==1.12
- torch==2.1.0
- triton==2.1.0
- typing-extensions==4.8.0
- numpy
prefix: /opt/conda/envs/exllama