Search results

ggml_metal_library_compile_pipeline: failed to compile pipeline: for LFM2-8B-A1B-Q8_0.gguf

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

bugSomething isn't workingSomething isn't working

Status: Open.

Bug

#17603 In ggml-org/llama.cpp;

· leok7v opened on Nov 29, 2025

Feature Request: LAMA_LOG_FILE env variable.

enhancementNew feature or requestNew feature or request

good first issueGood for newcomersGood for newcomers

help wantedNeeds help from the communityNeeds help from the community

Status: Open.

Feature

#17601 In ggml-org/llama.cpp;

· darkfibre-nl opened on Nov 29, 2025

[ANALYSE] wrong perf on quantized model with rocm 7.10/7.11

Status: Open.

#17596 In ggml-org/llama.cpp;

· Djip007 opened on Nov 29, 2025

Eval bug: Segmentation fault qwen3 next rocm/hip gfx906

bugSomething isn't workingSomething isn't working

need feedbackTesting and feedback with results are neededTesting and feedback with results are needed

Status: Open.

Bug

#17586 In ggml-org/llama.cpp;

· fuutott opened on Nov 29, 2025

Eval bug: Running llama-server only possible with single AMD GPU, running multiple always causes Segmentation fault regardless of model size

bugSomething isn't workingSomething isn't working

need more infoThe OP should provide more details about the issueThe OP should provide more details about the issue

Status: Open.

Bug

#17583 In ggml-org/llama.cpp;

· Zubkover opened on Nov 28, 2025

Qwen3-Next --ubatch-size issue

bugSomething isn't workingSomething isn't working

modelModel specificModel specific

Status: Open.

Bug

#17578 In ggml-org/llama.cpp;

· 2432896620-ctrl opened on Nov 28, 2025

Misc. bug: Librechat + Filesystem MCP + llama-server Fails Due to Invalid Schema

bugSomething isn't workingSomething isn't working

medium severityUsed to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)

server/api

Status: Open.

Bug

#17574 In ggml-org/llama.cpp;

· chadvoegele opened on Nov 28, 2025

Feature Request: Support dots.ocr

enhancementNew feature or requestNew feature or request

help wantedNeeds help from the communityNeeds help from the community

modelModel specificModel specific

Status: Open.

Feature

#17564 In ggml-org/llama.cpp;

· congson1293 opened on Nov 28, 2025

Eval bug: Qwen Models segfault on Vulkan

bugSomething isn't workingSomething isn't working

high severityUsed to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)

VulkanIssues specific to the Vulkan backendIssues specific to the Vulkan backend

Status: Open.

Bug

#17561 In ggml-org/llama.cpp;

· leuchtetgruen opened on Nov 27, 2025

Feature Request: Support Vibethinker-1.5B

enhancementNew feature or requestNew feature or request

good first issueGood for newcomersGood for newcomers

help wantedNeeds help from the communityNeeds help from the community

low severityUsed to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)

server

Status: Open.

Feature

#17560 In ggml-org/llama.cpp;

· Ricookies707 opened on Nov 27, 2025

Feature Request: chat format for INTELLECT-3

enhancementNew feature or requestNew feature or request

Status: Open.

Feature

#17559 In ggml-org/llama.cpp;

· pwilkin opened on Nov 27, 2025

Misc. bug: Regression on file uploads

bugSomething isn't workingSomething isn't working

low severityUsed to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)

server/webui

Status: Open.

Bug

#17556 In ggml-org/llama.cpp;

· pwilkin opened on Nov 27, 2025