Update README.md to include missing flags (#2449)

This commit is contained in:
jllllll 2023-05-31 09:07:56 -05:00 committed by GitHub
parent 6627f7feb9
commit 412e7a6a96
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -266,6 +266,13 @@ Optionally, you can use the following command-line flags:
| `--warmup_autotune` | (triton) Enable warmup autotune. | | `--warmup_autotune` | (triton) Enable warmup autotune. |
| `--fused_mlp` | (triton) Enable fused mlp. | | `--fused_mlp` | (triton) Enable fused mlp. |
#### AutoGPTQ
| Flag | Description |
|------------------|-------------|
| `--autogptq` | Use AutoGPTQ for loading quantized models instead of the internal GPTQ loader. |
| `--triton` | Use triton. |
#### FlexGen #### FlexGen
| Flag | Description | | Flag | Description |
@ -308,6 +315,8 @@ Optionally, you can use the following command-line flags:
|---------------------------------------|-------------| |---------------------------------------|-------------|
| `--api` | Enable the API extension. | | `--api` | Enable the API extension. |
| `--public-api` | Create a public URL for the API using Cloudfare. | | `--public-api` | Create a public URL for the API using Cloudfare. |
| `--api-blocking-port BLOCKING_PORT` | The listening port for the blocking API. |
| `--api-streaming-port STREAMING_PORT` | The listening port for the streaming API. |
#### Multimodal #### Multimodal