tabby/website/docs/faq.mdx
GlaserTools b3019aca2c
docs: faq.mdx load model from local directory (#1536)
* Update faq.mdx

Local model.json path description added

* Update faq.mdx

added information about MODEL_SPEC.md

* Update website/docs/faq.mdx

* Update faq.mdx

---------

Co-authored-by: Meng Zhang <meng@tabbyml.com>
2024-02-25 02:53:13 -08:00

52 lines
2.3 KiB
Plaintext
Vendored

import Collapse from '@site/src/components/Collapse';
# ⁉️ Frequently Asked Questions
<Collapse title="How much VRAM a LLM model consumes?">
By default, Tabby operates in int8 mode with CUDA, requiring approximately 8GB of VRAM for CodeLlama-7B.
For ROCm the actual limits are currently largely untested, but the same CodeLlama-7B seems to use 8GB of VRAM as well on a AMD Radeon™ RX 7900 XTX according to the ROCm monitoring tools.
</Collapse>
<Collapse title="What GPUs are required for reduced-precision inference (e.g int8)?">
* int8: Compute Capability >= 7.0 or Compute Capability 6.1
* float16: Compute Capability >= 7.0
* bfloat16: Compute Capability >= 8.0
To determine the mapping between the GPU card type and its compute capability, please visit [this page](https://developer.nvidia.com/cuda-gpus)
</Collapse>
<Collapse title="How to utilize multiple NVIDIA GPUs?">
Tabby only supports the use of a single GPU. To utilize multiple GPUs, you can initiate multiple Tabby instances and set CUDA_VISIBLE_DEVICES (for cuda) or HIP_VISIBLE_DEVICES (for rocm) accordingly.
</Collapse>
<Collapse title="My AMD device isn't supported by ROCm">
You can use the HSA_OVERRIDE_GFX_VERSION variable if there is a similar GPU that is supported by ROCm you can set it to that.
For example for RDNA2 you can set it to 10.3.0 and to 11.0.0 for RDNA3.
</Collapse>
<Collapse title="How can I convert my own model for use with Tabby?">
Since version 0.5.0, Tabby's inference now operates entirely on llama.cpp, allowing the use of any GGUF-compatible model format with Tabby. To enhance accessibility, we have curated models that we benchmarked, available at [registry-tabby](https://github.com/TabbyML/registry-tabby)
Users are free to fork the repository to create their own registry. If a user's registry is located at `https://github.com/USERNAME/registry-tabby`, the model ID will be `USERNAME/model`.
For details on the registry format, please refer to [models.json](https://github.com/TabbyML/registry-tabby/blob/main/models.json)
</Collapse>
<Collapse title="Can I use local model with Tabby?">
Tabby also supports loading models from a local directory that follow our specifications as outlined in [MODEL_SPEC.md](https://github.com/TabbyML/tabby/blob/main/MODEL_SPEC.md).
</Collapse>