LM Studio 0.4.15

0.4.15 - Release Notes

Build 2

• [CUDA] Added tensor parallelism support for multi-GPU model loading
• [llama.cpp] Added a Physical Batch Size advanced load option
• Fixed REST API requests hanging when HTTP/2 clients sent upgrade headers
• Fixed image attachments appearing in reverse order after sending a chat message
• Fixed a bug where double clicking model trigger would re-open it
• Fixed tool type error bug while using codex --oss
• Fixed invalid role error while using Claude Code. /v1/messages API now supports system messages in the messages array

Build 1

• LM Studio Engine Protocol beta 2
  • New architecture to enable us to ship more frequent engine updates
  • Turn it on in Settings > Developer > Enable LM Studio Engine Protocol
• Fixed a bug which dropped prompt cache on every message when using Claude Code, improving performance significantly
• Fixed a bug when using theme picker overlay over other modals
• Fixed a z-index bug in the Models Table scroll
• Security hardening