Format config and add vllm backend

ModelTC · Sep 5, 2024 · df20a6e · df20a6e
1 parent 14fba51
commit df20a6e
Show file tree

Hide file tree

Showing 96 changed files with 1,232 additions and 1,075 deletions.
diff --git a/configs/quantization/Awq/awq_w4a16.yml b/configs/quantization/Awq/awq_w4a16.yml
diff --git a/configs/quantization/Awq/awq_w4a16_fakequant_eval.yml b/configs/quantization/Awq/awq_w4a16_fakequant_eval.yml
diff --git a/configs/quantization/Awq/awq_w4a16_fakequant_eval_general_custom.yml b/configs/quantization/Awq/awq_w4a16_fakequant_eval_general_custom.yml
diff --git a/configs/quantization/Awq/awq_w4a16_fakequant_eval_opencompass.yml b/configs/quantization/Awq/awq_w4a16_fakequant_eval_opencompass.yml
diff --git a/configs/quantization/Awq/awq_w8a8_fakequant_eval_general.yml b/configs/quantization/Awq/awq_w8a8_fakequant_eval_general.yml
diff --git a/configs/quantization/FP/awq_we2m1a16_128_fakequant_eval.yml b/configs/quantization/FP/awq_we2m1a16_128_fakequant_eval.yml
diff --git a/configs/quantization/FP/rtn_w8a8_fakequant_eval.yml b/configs/quantization/FP/rtn_w8a8_fakequant_eval.yml
diff --git a/configs/quantization/FP/rtn_we2m1a16_fakequant_eval.yml b/configs/quantization/FP/rtn_we2m1a16_fakequant_eval.yml
diff --git a/configs/quantization/GPTQ/gptq_w4a16_fakequant_eval_general.yml b/configs/quantization/GPTQ/gptq_w4a16_fakequant_eval_general.yml
diff --git a/configs/quantization/OmniQuant/omniq_llama_w2a16_fakequant_eval.yml b/configs/quantization/OmniQuant/omniq_llama_w2a16_fakequant_eval.yml