Open sourceOpen-source releaseEfficiency & Inference1 source · Aug 11, 2026

vllm-project/vllm v0.27.1

Support quantized DSpark Markov heads (#50424)

vLLMQuantization
ProofCode ↗
Read at GitHub: vllm-project/vllm ↗← Today

Key points

  • This is a patch release on top of v0.27.0.

Sources (1)

  • [1]vllm-project/vllm v0.27.1
    GitHub: vllm-project/vllm · Aug 11, 10:47 AM
    - Support quantized DSpark Markov heads (#50424)
    This is a patch release on top of v0.27.0.

Extractive summary: sentences quoted from the sources.

Before this

  1. Aug 10, 2026vllm-project/vllm v0.27.0
  2. Jul 11, 2026vllm-project/vllm v0.25.0
  3. Jun 29, 2026vllm-project/vllm v0.24.0
  4. Jun 15, 2026vllm-project/vllm v0.23.0
  5. May 29, 2026vllm-project/vllm v0.22.0
  6. Apr 27, 2026vllm-project/vllm v0.20.0

Related

GitHub: vllm-project/vllm6d ago

vllm-project/vllm v0.31.0

Code
GitHub: vllm-project/vllm19d ago

vllm-project/vllm v0.30.0

Code
Paper
arXiv (AI, ML, NLP, CV, robotics, multi-agent)5d ago

OSFP4: Joint Optimization of Diagonal Smoothing and Block Scales for NVFP4 Quantization

Paper
Paper
arXiv (AI, ML, NLP, CV, robotics, multi-agent)5d ago

Q-PACE: Dynamic Precision Allocation for Quantization-Aware Training

Paper