v0.10.1

v0.10.1 vllm-project / vllm Public Uh oh! There was an error while loading.

This ModelRelease is relevant to the technology intelligence record because it involves DeepSeek, Meta, NVIDIA, AMD. The source article should remain the factual reference for follow-up coverage.

• vllm-project / vllm Public Uh oh!
• There was an error while loading.
• Notifications You must be signed in to change notification settings Fork 22.7k Star 92.7k v0.10.1 github-actions released this 18 Aug 04:39 · 13353 commits to main since this release v0.10.1 aab5498 Highlights v0.10.1 release includes 727 commits, 245 committers (105 new contributors).
• NOTE: This release deprecates V0 FA3 support and as a result FP8 kv-cache in V0 may have issues Model Support New model families : GPT-OSS with comprehensive tool calling and streaming support ( #22327 , #22330 , #22332 , #22335 , #22339 , #22340 , #22342 ), Command-A-Vision ( #22660 ), mBART ( #22883 ), and SmolLM3 using Transformers backend ( #22665 ).
• Vision-language models : Official Eagle multimodal support with Llama4 backend ( #20788 ), Step3 vision-language models ( #21998 ), Gemma3n multimodal ( #20495 ), MiniCPM-V 4.0 ( #22166 ), HyperCLOVAX-SEED-Vision-Instruct-3B ( #20931 ), Emu3 with Transformers backend ( #21319 ), Intern-S1 ( #21628 ), and Prithvi in online serving mode ( #21518 ).
• Enhanced existing models : NemotronH support ( #22349 ), Ernie 4.5 Base 0.3B model name change ( #21735 ), GLM-4.5 series improvements ( #22215 ), Granite models with fused MoE configurations ( #21332 ) and quantized checkpoint loading ( #22925 ), Ultravox support for Llama 4 and Gemma 3 backends ( #17818 ), Mamba1 and Jamba model support in V1 (without CUDA graphs) ( #21249 ) Advanced model capabilities : Qwen3 EPLB ( #20815 ) and dual-chunk attention support ( #21924 ), Qwen native Eagle3 target support ( #22333 ).