Repository Issue Activity (beta)

#634 "lms get" command unable to saturate 10gbit connection

#632 lms-key-2 not generated if more than one user installs llmster on server

#633 The program is getting worse and worse in design

#631 Feature request: detect outdated downloaded models and support force re-fetching them

#630 Feature Request - LM Link able to use MCPs from MCP.json. via locally app etc.

#615 very very very slow download speed

#625 AMD Radeon RX 6800 not working with ROCm v2.29.0 or any newer ver. after v2.1.0 On LM STUDIO

#583 LM Studio + diffusion_gemma

#628 Incorrect total disk space reported by "ls --variants" when several variants exist

#626 IT'S TIME TO ADD INTEL SYCL Llama Runtime support!

#614 LM Studio in server mode for Granite Docling to process PDF files

#206 Get Gated Model

#624 Error: Failed to resolve artifact "brius/web-search": Sorry, LM Studio plugins are not supported in Bionic.

#158 Video Understanding Support

#188 Add a parameter for thinking effort to the generation settings

#619 Feature request: expose extra llama-server arguments in Load settings UI

#623 It is recommended to support model files in ConvRot format.

#622 Cannot stop lms server from command line, if listening only on specific network interface (--bind option)

#613 Gemma4Assistant requires ctx_other to be set during model loading

#521 [Feature Request] Add rerank API endpoint (e.g., /v1/rerank) for reranking models

#620 How to load the mp4 file and make its use possible in LMSTUDIO IMAGE APP

#610 Speculative Decoding crash with Gemma 4 MTP Draft Model ("failed to process speculative batch")

#568 RTL (right-to-left) automatic detection for setting text direction

#617 Unable to modify timeout setting in LM Studio

#589 [Bug] Strix Halo APU: llama.cpp ROCm runtime does not recognize shared/unified memory when BIOS GPU allocation is set to Auto