docs(readme): add openinfer (Rust) as a DFlash backend#141
Open
xiaguan wants to merge 1 commit into
Open
Conversation
openinfer (https://github.com/openinfer-project/openinfer) is a pure Rust + CUDA inference engine with native DFlash support for Qwen3-4B/8B, using the z-lab/Qwen3-{4B,8B}-DFlash-b16 drafters. Adds a short Quick Start entry alongside the existing backends. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
xiaguan
force-pushed
the
docs/openinfer-backend
branch
from
6fb4cbd to
150648f
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hi DFlash team — thanks for the work on DFlash, and for releasing the Qwen3-4B/8B
-b16drafters.We added native DFlash speculative decoding to openinfer, a from-scratch LLM inference engine in pure Rust + CUDA (no PyTorch). It runs the
z-lab/Qwen3-{4B,8B}-DFlash-b16drafters behind a--dflash-draft-model-pathflag; single-stream decode comes out to 1.82× on an RTX 5070 Ti and 1.56× on a 5090.This PR adds a short openinfer (Rust) entry to the Quick Start, after the existing backends, so DFlash users on NVIDIA GPUs have the option. Happy to adjust the wording or placement however you'd prefer — and thanks again for making DFlash easy to integrate.