Search results

Eval bug: Devstral diverges from reference implementation

bugSomething isn't workingSomething isn't working

modelModel specificModel specific

Status: Open.

#17980 In ggml-org/llama.cpp;

· pwilkin opened on Dec 12, 2025

Misc. bug: llama-cli --completion-bash wont work without a model as argument

bug-unconfirmed

Status: Open.

#17973 In ggml-org/llama.cpp;

· teto opened on Dec 12, 2025

Eval bug: [Router] Claude Code - model not found - invalid_request_error

bug-unconfirmed

Status: Open.

#17968 In ggml-org/llama.cpp;

· isgallagher opened on Dec 12, 2025

Feature Request: Add Ivy Bridge/Piledriver CPU backends when <code>GGML_CPU_ALL_VARIANTS=ON</code>

enhancementNew feature or requestNew feature or request

Status: Open.

#17966 In ggml-org/llama.cpp;

· bberberov opened on Dec 12, 2025

Misc. bug: WebUI Model Information is unclickable (shows 'not-allowed' cursor)

bug-unconfirmed

Status: Open.

#17963 In ggml-org/llama.cpp;

· hashms0a opened on Dec 12, 2025

Misc. bug: WebUI load of any model fails on &gt;= b7352 if local host's ip is specified by external interface

bug-unconfirmed

Status: Open.

#17962 In ggml-org/llama.cpp;

· wbtek opened on Dec 12, 2025

Eval bug: Devstral-Small-2-24B-Instruct-2512 doesn't pass the example tool call tests

bug-unconfirmed

Status: Open.

#17960 In ggml-org/llama.cpp;

· blakkd opened on Dec 12, 2025

Misc. bug: Misc. bug: llama-speculative-simple not working on Nvidia with Vulkan after b7063

bugSomething isn't workingSomething isn't working

VulkanIssues specific to the Vulkan backendIssues specific to the Vulkan backend

Status: Open.

#17957 In ggml-org/llama.cpp;

· nikomartn opened on Dec 12, 2025

make install: llama-server: error while loading shared libraries: libmtmd.so.0: cannot open shared object file: No such file or directory

bug-unconfirmed

Status: Open.

#17950 In ggml-org/llama.cpp;

· codeliger opened on Dec 12, 2025

Feature Request: Default config for --model-presets

enhancementNew feature or requestNew feature or request

server

server/api

Status: Open.

#17948 In ggml-org/llama.cpp;

· eleqtrizit opened on Dec 11, 2025

Feature Request: server/webui: allow configuring server props (default webui settings) from CLI args

enhancementNew feature or requestNew feature or request

server

server/api

server/webui

Status: Open.

#17940 In ggml-org/llama.cpp;

· woof-dog opened on Dec 11, 2025

Feature Request: Qwen3-Next: CPU performance optimization

enhancementNew feature or requestNew feature or request

Status: Open.

#17936 In ggml-org/llama.cpp;

· jdvpro opened on Dec 11, 2025