vllm-project/vllm v0.19.2rc0: [Bugfix] Fix k_proj's bias for GLM-ASR (#40160)

GitHub Releases Watchlist Tools

Summary

vLLM v0.19.2rc0 release candidate includes a bugfix for k_proj's bias handling in GLM-ASR models, addressing a specific compatibility issue in the LLM serving framework.

Signed-off-by: Rishapveer Singh [email protected]
Original Article
View Cached Full Text

Cached at: 04/20/26, 08:36 AM

Easy, fast, and cheap LLM serving for everyone

| Documentation | Blog | Paper | Twitter/X | User Forum | Developer Slack |

Similar Articles

vllm-project/vllm v0.21.0rc1

GitHub Releases Watchlist

vLLM v0.21.0rc1 is a pre-release update for the high-performance LLM inference and serving library, featuring optimizations for throughput, quantization, and hardware support.

vllm-project/vllm v0.20.1

GitHub Releases Watchlist

vLLM v0.20.1 is a minor version update for the popular open-source LLM inference and serving library, maintaining its focus on high-throughput and efficient memory management.

vllm-project/vllm v0.20.0rc1

GitHub Releases Watchlist

vLLM 0.20.0rc1 releases with major throughput, quantization, speculative decoding, and multi-hardware support enhancements for scalable LLM serving.

vllm-project/vllm v0.19.1

GitHub Releases Watchlist

vLLM v0.19.1 release - a fast and easy-to-use open-source library for LLM inference and serving with state-of-the-art throughput, supporting 200+ model architectures and diverse hardware including NVIDIA/AMD GPUs and CPUs.