Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
models-large.txt 367 Bytes
Newer Older
Dipika Sikka's avatar
[Misc] Fused MoE Marlin support for GPTQ (#8217)  
Dipika Sikka committed
1
2 
compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-quantized, main
compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-channel-quantized, main
ElizaWszola's avatar
[Kernel] Enable 8-bit weights in Fused Marlin MoE (#8032)  
ElizaWszola committed
3 
compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W8A16-quantized, main
Michael Goin's avatar
[Misc] Support FP8 MoE for compressed-tensors (#8588)  
Michael Goin committed
4 
compressed-tensors, mgoin/DeepSeek-Coder-V2-Lite-Instruct-FP8, main
ElizaWszola's avatar
[Kernel] Enable 8-bit weights in Fused Marlin MoE (#8032)  
ElizaWszola committed
5 
gptq_marlin, TheBloke/Mixtral-8x7B-v0.1-GPTQ, main