Tags: 1b5d/llm-api
Toggle 0.1.2's commit message
GH actions free up disk space (#18 )
* gh actions free up disk space
* cleanup free disk space commands
* cleanup free disk space commands
Toggle 0.1.1's commit message
Update readme and bump dep version (#14 )
* update readme and bump dep version
* upgrade GPU dockerfile
Toggle 0.1.0's commit message
Release 0.1.0 (#12 )
* fix gh actions
* remove arm64 from gpu build
* cleanup
* enable cache for docker build on gha
* refine docker build cache ref
* refine gpu dependencies
* quite conda installations
* free disk space on gha
* fix free space command on gha
* fix free space command on gha
Toggle 0.0.4-gptq-llama-triton's commit message
Toggle 0.0.4's commit message
move from cuda to triton in regards to GPTQ for Llama
Toggle 0.0.3-gptq-llama-cuda's commit message
add a separate parameter for safetensors models
Toggle 0.0.2-gptq-llama-cuda's commit message
rebuild the cuda based image
Toggle 0.0.1-gptq-llama-cuda's commit message
fix noop placeholder in gptq vendor code
Toggle 0.0.1's commit message
add gh actions for release
You can’t perform that action at this time.