Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-26 09:40:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add note about --no-fused_mlp ignoring --gpu-memory (#1301)

Browse Source
This commit is contained in:
practicaldreamer 2023-04-17 08:46:37 -05:00 committed by GitHub
parent b57ffc2ec9
commit 3961f49524
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -238,7 +238,7 @@ Optionally, you can use the following command-line flags:
| `--pre_layer PRE_LAYER` | GPTQ: The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models. | | `--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-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-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. | | `--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. | | `--monkey-patch` | GPTQ: Apply the monkey patch for using LoRAs with quantized models. |
#### FlexGen #### FlexGen