Skip to content

Issues: mlc-ai/mlc-llm

Project Tracking
#647 opened Aug 2, 2023 by tqchen
Open
Model Request Tracking
#1042 opened Oct 9, 2023 by CharlieFRuan
Open 4
Beta
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

249 Open 1,264 Closed
249 Open 1,264 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Bug] Cannot auto device detect without internet bug Confirmed bugs
#3214 opened Apr 26, 2025 by Raviu56
[Model Request] nemotron-nas new-models
#3213 opened Apr 24, 2025 by iEddie-cmd
[Bug] Speculative decoding not working due to difference in vocab_size (Qwen2.5 serie) bug Confirmed bugs
#3212 opened Apr 22, 2025 by glennhanks
1
[Question] Should we expect generation quality comparable to gguf with 4-bit quantization? question Question about the usage
#3210 opened Apr 18, 2025 by bene-ges
[Question] question Question about the usage
#3209 opened Apr 18, 2025 by haoxuanWeng
Failed mlc build from source with CUTLASS enabled bug Confirmed bugs
#3208 opened Apr 18, 2025 by notabd7-deepshard
1
[Model Request] BitNet b1.58 2B4T - Scaling Native 1-bit LLM new-models
#3207 opened Apr 17, 2025 by pikann
[Bug] Trouble to run mlc_llm chat with Gemma 3 models bug Confirmed bugs
#3206 opened Apr 16, 2025 by grf53
4
[Bug] Missing post layernorm in CLIP model bug Confirmed bugs
#3205 opened Apr 16, 2025 by vincentccc
[Bug] CMake Error at 3rdparty/tokenizers-cpp/msgpack/CMakeLists.txt during CMake iOS bug Confirmed bugs
#3204 opened Apr 15, 2025 by KingSlayer06
2
[Bug] Rope doesn't work for llama-3 bug Confirmed bugs
#3202 opened Apr 14, 2025 by bene-ges
1
[Bug] Can't use App caused by No implementation found for int org.apache.tvm.LibInfo.nativeLibInit(java.lang.String) bug Confirmed bugs
#3201 opened Apr 13, 2025 by jordanqi
[Bug] can't find crate for 'core' when cross-compiling for aarch64-linux-android during package bug Confirmed bugs
#3200 opened Apr 13, 2025 by jordanqi
启动app时报错（class文件空指针异常） bug Confirmed bugs
#3199 opened Apr 12, 2025 by Myl-Ma
[Question] Does MLC-LLM support multi nodes parallel? question Question about the usage
#3198 opened Apr 10, 2025 by shengxinhu
[Model Request] SmolDocling-256M-preview new-models
#3194 opened Apr 1, 2025 by temsa
[Question] no convert Qwen2.5-Omni-7B question Question about the usage
#3193 opened Apr 1, 2025 by hlovingness
[Question] How to evaluate the accuracy of models??? question Question about the usage
#3188 opened Mar 24, 2025 by kunxiongzhu
1
[Bug] Binary was created using {relax.Executable} but a loader of that name is not registered. Available loaders are relax.VMExecutable, const_loader, static_library, metal. Perhaps you need to recompile with this runtime enabled. bug Confirmed bugs
#3186 opened Mar 21, 2025 by Japp-Galang
7
[Bug] TVMError: Check failed: (!support_sliding_window_) is false: Kernel BeginForward doesn't support sliding window bug Confirmed bugs
#3184 opened Mar 19, 2025 by FFchopon
[Bug] The response often gets trapped in an infinite loop error when running models using mlc-llm bug Confirmed bugs
#3183 opened Mar 19, 2025 by FFchopon
[Bug] gemma3 WebGPU <unnamed> panicked bug Confirmed bugs
#3182 opened Mar 18, 2025 by nico-martin
2
[Bug] llama3: same text tokenize to different token cause prefix cache match fail. bug Confirmed bugs
#3179 opened Mar 17, 2025 by sunzj
2
[Bug] clang linker error upon running any model in Windows bug Confirmed bugs
#3177 opened Mar 16, 2025 by TheOtherGuy
2
[Question] Does it support multi-gpu (intel ARC A770)? question Question about the usage
#3175 opened Mar 14, 2025 by savvadesogle
1
ProTip! Mix and match filters to narrow down what you’re looking for.