# Furiosa SDK 2025.1.0 release

**URL:** <https://forums.furiosa.ai/t/furiosa-sdk-2025-1-0-release/253>\
**Category:** Announcements\
**Tags:** release\
**Created:** [February 24, 2025, 8:02am UTC](https://forums.furiosa.ai/t/furiosa-sdk-2025-1-0-release/253 "2025-02-24T08:02:09Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![hyunsik](https://yyz1.discourse-cdn.com/flex031/user_avatar/forums.furiosa.ai/hyunsik/32/6_2.png) [@hyunsik](https://forums.furiosa.ai/u/hyunsik)\
**Post date:** [February 24, 2025, 8:02am UTC](https://forums.furiosa.ai/t/furiosa-sdk-2025-1-0-release/253/1 "2025-02-24T08:02:09Z")

</div>

Hello! We are excited to announce the [Furiosa SDK 2025.1.0 release](https://developer.furiosa.ai/v2025.1.0/en/whatsnew/index.html#furiosa-sdk-2025-1-0-beta1-2025-02-24). SDK 2025.1.0 has officially been published today. This release is the third major release for the RNGD, and provides the streamlined stack to enable LLM on RNGD, including driver, SoC FW, PERT, HAL, cloud-native components, Model Compressor, Furiosa Compiler, and Furiosa LLM.

Here are the release notes are documents:

- [Release Note (2025.1.0)](https://developer.furiosa.ai/v2025.1.0/en/whatsnew/index.html#furiosa-sdk-2025-1-0-beta1-2025-02-24)
- [Upgrading FuriosaAI’s Software (2025.1.0)](https://developer.furiosa.ai/v2025.1.0/en/getting_started/upgrade_guide.html)
- [Developer Center (2025.1.0)](https://developer.furiosa.ai/v2025.1.0/en/index.html)

Key features and improvements in the 2025.1.0 release

- LLM Latency Optimization (Up to 11.66% TTFT, 11.45% TPOT improvement for `<=` 30k inputs, 1k outputs)
- Support Tool-calling in Furiosa LLM ([Tool Calling](https://developer.furiosa.ai/v2025.1.0/en/furiosa_llm/furiosa-llm-serve.html#toolcalling))
- Support Device remapping (e.g., `/dev/rngd/npu2pe0-3` → `/dev/rngd/npu0pe0-3`) for container
- Add the new command line tool `furiosa-llm build` to build easily an artifact from Hugging Face model ([Building a Model Artifact](https://developer.furiosa.ai/v2025.1.0/en/furiosa_llm/model-preparation-workflow.html#buildingmodelartifact))
- Fix continuous batch scheduling bugs which occur in certain ranges of sequence lengths and batch sizes
- Automatic configuration of the maximum KV-cache memory allocation
- Reduce the fragmentations of runtime memory allocation
- Allow `furiosa-mlperf` command to specify `pipeline_parallel_size` and `data_parallel_size`
- Add `--allowed-origins` argument to `furiosa-llm serve` ([OpenAI-Compatible Server](https://developer.furiosa.ai/v2025.1.0/en/furiosa_llm/furiosa-llm-serve.html#openaiserver))
- Fix `trust_remote_code` support bug in furiosa-llm
- Support Min-p sampling in `SamplingParams` ([SamplingParams class](https://developer.furiosa.ai/v2025.1.0/en/furiosa_llm/reference/sampling_params.html#samplingparams))
- **Allow** `npu:X` **in addition to** `npu:X:*` **in** `devices` **option**
  - e.g., `furiosa-llm serve ./model --devices "npu:0"`

- `fuiorsa-mlperf` command supports `npu_q_limit`, `spare_ratio`, allowing to optimize the performance