diff --git a/README.md b/README.md
index 7d5c469..0f163b1 100644
--- a/README.md
+++ b/README.md
@@ -232,14 +232,14 @@ Optionally, you can use the following command-line flags:
 
 | Flag                      | Description |
 |---------------------------|-------------|
-| `--wbits WBITS`           | GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. |
-| `--model_type MODEL_TYPE` | GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported. |
-| `--groupsize GROUPSIZE`   | GPTQ: Group size. |
-| `--pre_layer PRE_LAYER`   | GPTQ: The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models. |
-| `--no-quant_attn`         | GPTQ: Disable quant attention for triton. If you encounter incoherent results try disabling this. |
-| `--no-warmup_autotune`    | GPTQ: Disable warmup autotune for triton. |
-| `--no-fused_mlp`          | GPTQ: Disable fused mlp for triton. If you encounter "Unexpected mma -> mma layout conversion" try disabling this. Disabling may also help model splitting for multi-gpu setups.|
-| `--monkey-patch`          | GPTQ: Apply the monkey patch for using LoRAs with quantized models. |
+| `--wbits WBITS`           | Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. |
+| `--model_type MODEL_TYPE` | Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported. |
+| `--groupsize GROUPSIZE`   | Group size. |
+| `--pre_layer PRE_LAYER`   | The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models. |
+| `--monkey-patch`          | Apply the monkey patch for using LoRAs with quantized models.
+| `--no-quant_attn`         | (triton) Disable quant attention. If you encounter incoherent results try disabling this.
+| `--no-warmup_autotune`    | (triton) Disable warmup autotune.
+| `--no-fused_mlp`          | (triton) Disable fused mlp. If you encounter "Unexpected mma -> mma layout conversion" try disabling this.
 
 #### FlexGen
 
diff --git a/modules/shared.py b/modules/shared.py
index ea55973..f068ec0 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -119,14 +119,14 @@ parser.add_argument('--trust-remote-code', action='store_true', help="Set trust_
 parser.add_argument('--threads', type=int, default=0, help='Number of threads to use in llama.cpp.')
 
 # GPTQ
-parser.add_argument('--wbits', type=int, default=0, help='GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
-parser.add_argument('--model_type', type=str, help='GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.')
-parser.add_argument('--groupsize', type=int, default=-1, help='GPTQ: Group size.')
-parser.add_argument('--pre_layer', type=int, default=0, help='GPTQ: The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models.')
-parser.add_argument('--no-quant_attn', action='store_true', help='GPTQ: Disable quant attention for triton. If you encounter incoherent results try disabling this.')
-parser.add_argument('--no-warmup_autotune', action='store_true', help='GPTQ: Disable warmup autotune for triton.')
-parser.add_argument('--no-fused_mlp', action='store_true', help='GPTQ: Disable fused mlp for triton. If you encounter "Unexpected mma -> mma layout conversion" try disabling this.')
-parser.add_argument('--monkey-patch', action='store_true', help='GPTQ: Apply the monkey patch for using LoRAs with quantized models.')
+parser.add_argument('--wbits', type=int, default=0, help='Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
+parser.add_argument('--model_type', type=str, help='Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.')
+parser.add_argument('--groupsize', type=int, default=-1, help='Group size.')
+parser.add_argument('--pre_layer', type=int, default=0, help='The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models.')
+parser.add_argument('--monkey-patch', action='store_true', help='Apply the monkey patch for using LoRAs with quantized models.')
+parser.add_argument('--no-quant_attn', action='store_true', help='(triton) Disable quant attention. If you encounter incoherent results try disabling this.')
+parser.add_argument('--no-warmup_autotune', action='store_true', help='(triton) Disable warmup autotune.')
+parser.add_argument('--no-fused_mlp', action='store_true', help='(triton) Disable fused mlp. If you encounter "Unexpected mma -> mma layout conversion" try disabling this.')
 
 # FlexGen
 parser.add_argument('--flexgen', action='store_true', help='Enable the use of FlexGen offloading.')