 AlpinDale
|
705821a7fe
feat: AQLM quantization support (#293)
|
hai 10 meses |
|
AlpinDale
|
ea0f57b233
feat: allow further support for non-cuda devices (#247)
|
hai 11 meses |
|
AlpinDale
|
7760913873
fix: garbage output from GPTQ (#245)
|
hai 11 meses |
|
AlpinDale
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
hai 11 meses |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
hai 11 meses |
|
AlpinDale
|
801eda0b7a
feat: support GPTQ 2, 3, and 8bit quants (#181)
|
hai 1 ano |
|
AlpinDale
|
7c6fdea535
fix: GPTQ warnings and exllama states (#171)
|
hai 1 ano |
|
AlpinDale
|
62b2c4119d
feat: re-write GPTQ and refactor exllama kernels (#152)
|
hai 1 ano |
|
AlpinDale
|
2b1ba581f9
feat: re-implement GPTQ (#141)
|
hai 1 ano |
