orthrus

[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.

chiennv2000/orthrus

View on GitHub ↗

[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.

orthrus grew +0.4% in the last 30 days, ranks 107th of 343 in Inference Optimization, last commit 101 days ago.

Star trajectory

82 days tracked
2026-08-31484 stars today2026-11-22
Momentum

+0.4% in 30d, below the Inference Optimization median of +1.6%.

Maintenance

Last commit 101 days ago, staler than the median of 16d.

How it compares in Inference Optimization

orthrus
484
stars
+0.4% 30d
commit 101 days ago
Inference Optimization median
242
stars
+1.6% 30d
commit ~16d ago
Leader · supertonic
13.8k
stars
-0.1% 30d
commit 74 days ago

Ranked 107th of 343 by stars.

Ranked by shared tags, then keywords, then stars
  1. Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127…

    +592 (+27%) in 30d · Committed 12d ago · Python · Apache-2.0

    Shares Inference Optimization, Model Optimization

  2. 一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework

    +17 (+0.9%) in 30d · Committed 2d ago · C++ · Apache-2.0

    Shares Model Optimization, Inference Optimization

  3. MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and…

    +1 (+0.1%) in 30d · Committed 82d ago · Python · Apache-2.0

    Shares Model Optimization, Inference Optimization

  4. RDNA-native LLM inference engine in Rust.

    +95 (+13%) in 30d · Committed today · Rust · Other license

    Shares Inference Optimization, Model Optimization

  5. From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP…

    -2 (-0.4%) in 30d · Committed 43d ago · Python · Other license

    Shares Inference Optimization, Model Optimization

  6. Alzeo is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo…

    +36 (+15%) in 30d · Committed 2d ago · Python · MIT

    Shares Inference Optimization, Model Optimization

  7. Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one…

    +31 (+18%) in 30d · Committed today · Python · Apache-2.0

    Shares Inference Optimization, Model Optimization

  8. Pinned Intel Arc Pro B60/B70 inference recipes, engine patches and measurement records: Qwen3.8-27B EXL3 on…

    +20 (+11%) in 30d · Committed today · Python · MIT

    Shares Inference Optimization, Model Optimization

  9. GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K…

    +0 (+0.0%) in 30d · Committed 156d ago · Shell

    Shares Inference Optimization, Model Optimization

  10. Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K…

    +22 (+18%) in 30d · Committed 37d ago · Python · Apache-2.0

    Shares Inference Optimization, Model Optimization

Language
Python
License
MIT License
Contributors
2
Forks
23
Watchers
18
Open issues
3
Releases
0
Created
2026-05-13
Stars this week
+2

You've seen where orthrus stands today.

Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain orthrus?

Claim this page to add your own call-to-action.

Claim this page