@dbreunig: Big release with RLM improvements, optimization chaining, the start of LiteLLM decoupling, and 24 first-time contributo…
Summary
Major open-source release featuring RLM improvements, optimization chaining, and initial LiteLLM decoupling with 24 new contributors.
View Cached Full Text
Cached at: 04/22/26, 06:20 AM
Big release with RLM improvements, optimization chaining, the start of LiteLLM decoupling, and 24 first-time contributors!
Similar Articles
@vllm_project: vLLM v0.21.0 is out! 367 commits from 202 contributors (49 new). Highlights: KV Offload + HMA, spec decode with thinkin…
vLLM v0.21.0 has been released with KV Offload + HMA, speculative decoding with thinking budget for reasoning models, TOKENSPEED_MLA on Blackwell for DSR1/Kimi K2.5, Mooncake distributed KV, DeepSeek V4 pipeline parallelism, and a C++20 + Transformers v5 baseline.
@diblacksmith: [OSS RELEASE] This is my story of how I've been using RLMs at work. Since its launch (Jan26), I started using it for da…
The author shares his experience using RLMs for daily tasks like coding, processing multi-million-token logs, and browser automation, and releases it as an open-source Python package installable via pip.
@huang_chao4969: LightRAG v1.5 is here! The biggest release ever! 35k+ GitHub | 1.1M+ downloads | 251 contributors | 1.1k+ PRs merged He…
LightRAG v1.5 is released with six major improvements including multimodal document processing, enhanced parsing, and role-specific LLM configuration, making RAG simpler, faster, and more powerful.
@RedHat_AI: Michael Goin (@mgoin_) walks through @vllm_project v0.20.0. 752 commits. 320 contributors. 123 new. DeepSeek V4, TurboQ…
Michael Goin reviews the vLLM v0.20.0 release, highlighting 752 commits and new features like DeepSeek V4 support, TurboQuant, and PyTorch 2.11 integration.
@ggerganov: the 10000th release of llama.cpp
Celebrating the 10000th release of llama.cpp, a tool for running LLMs locally.