EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Support limiting max loaded loras in CPU. (#8650)

Browse Source
This commit is contained in:
Lifu Huang
2025-08-03 00:02:23 -07:00
committed by GitHub
parent a437aa9987
commit 8675bdf246
8 changed files with 163 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/backend/lora.ipynb
View File

@@ -33,6 +33,8 @@
"\n",
"* `max_loras_per_batch`: Maximum number of adaptors used by each batch. This argument can affect the amount of GPU memory reserved for multi-LoRA serving, so it should be set to a smaller value when memory is scarce. Defaults to be 8.\n",
"\n",
"* `max_loaded_loras`: If specified, it limits the maximum number of LoRA adapters loaded in CPU memory at a time. The value must be greater than or equal to `max-loras-per-batch`.\n",
"\n",
"* `lora_backend`: The backend of running GEMM kernels for Lora modules. It can be one of `triton` or `flashinfer`, and set to `triton` by default. For better performance and stability, we recommend using the Triton LoRA backend. In the future, faster backend built upon Cutlass or Cuda kernels will be added.\n",
"\n",
"* `max_lora_rank`: The maximum LoRA rank that should be supported. If not specified, it will be automatically inferred from the adapters provided in `--lora-paths`. This argument is needed when you expect to dynamically load adapters of larger LoRA rank after server startup.\n",

1
docs/backend/server_arguments.md
View File

@@ -181,6 +181,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| `--lora-target-modules` | The union set of all target modules where LoRA should be applied (e.g., `q_proj`, `k_proj`, `gate_proj`). If not specified, it will be automatically inferred from the adapters provided in `--lora-paths`. This argument is needed when you expect to dynamically load adapters of different target modules after server startup. You can also set it to `all` to enable LoRA for all supported modules. However, enabling LoRA on additional modules introduces a minor performance overhead. If your application is performance-sensitive, we recommend only specifying the modules for which you plan to load adapters. | None |
| `--lora-paths` | The list of LoRA adapters. You can provide a list of either path in str or renamed path in the format {name}={path}. | None |
| `--max-loras-per-batch` | Maximum number of adapters for a running batch, include base-only request. | 8 |
| `--max-loaded-loras` | If specified, it limits the maximum number of LoRA adapters loaded in CPU memory at a time. The value must be greater than or equal to `--max-loras-per-batch`. | None |
| `--lora-backend` | Choose the kernel backend for multi-LoRA serving. | triton |
## Kernel backend