-
Notifications
You must be signed in to change notification settings - Fork 1.4k
Issues: mlc-ai/mlc-llm
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Exiting all the time. Android, Redmi Note 13 pro plus [Bug]
bug
Confirmed bugs
#2558
opened Jun 9, 2024 by
condr-at
[Question] Is there a way to compute ppl of models in MLC-LLM?
question
Question about the usage
#2554
opened Jun 8, 2024 by
ponytaill
[Bug] Could NOT find Doxygen (missing: DOXYGEN_EXECUTABLE)
bug
Confirmed bugs
#2541
opened Jun 7, 2024 by
panghongtao
[Bug] Apple Metal/MPS -- TVM/MLC-LLM won't compile from source
bug
Confirmed bugs
#2540
opened Jun 7, 2024 by
BuildBackBuehler
[Question] Unable to download and compile custom model from Hugging Face using Question about the usage
mlc_llm package
command
question
#2525
opened Jun 6, 2024 by
AbhayGopal
[Bug] chatglm4 mlc_llm shows error "TVMError: Check failed: append_length > 0 (0 vs. 0) : Append with length 0 is not allowed." during mlc_llm chat CLI
bug
Confirmed bugs
#2517
opened Jun 6, 2024 by
lihaofd
[Question] Running mlc_llm into a multi-phase container build
question
Question about the usage
#2512
opened Jun 5, 2024 by
oglok
[Bug] FlashInfer decode BeginForward error an illegal instruction was encountered
bug
Confirmed bugs
#2509
opened Jun 4, 2024 by
zifeitong
[Feature Request] please allow f32q5_k and f16q5_k quantizations
feature request
New feature or request
#2506
opened Jun 4, 2024 by
0wwafa
[Bug] Confirmed bugs
mlc_llm serve
throws CUDA: invalid device ordinal
bug
#2498
opened Jun 3, 2024 by
josephrocca
[Question] Cannot compile custom model to work on web browser
question
Question about the usage
#2485
opened Jun 2, 2024 by
lawofcycles
[Doc] benchmark on different hardware
documentation
Improvements or additions to documentation
#2475
opened May 30, 2024 by
louis030195
[Doc] Request for suggested build-from-source options + explanation of added functionality
documentation
Improvements or additions to documentation
#2473
opened May 30, 2024 by
BuildBackBuehler
Compiling WebAssembly library with debug symbols/source map to aid in debugging
question
Question about the usage
#2472
opened May 30, 2024 by
slash-under
mlc_llm serve fails on concurrent users - Llama3 70B parameter hosting
bug
Confirmed bugs
#2462
opened May 29, 2024 by
swamysrivathsan
'ChatGLMTokenizer' object has no attribute 'backend_tokenizer'
bug
Confirmed bugs
#2460
opened May 29, 2024 by
lihaofd
[Doc] Python API KV/memory reset details absent
documentation
Improvements or additions to documentation
#2426
opened May 26, 2024 by
federicoparra
[Feature Request] phi-3 small realeased -> performs two times ebtter then Phi-3 mini
feature request
New feature or request
#2420
opened May 26, 2024 by
sebastienbo
Phi-2 q4f16_1 runs faster when compiled without Confirmed bugs
tvm.relax.transform.FuseOps()
and tvm.relax.transform.FuseTIR()
transformations
bug
#2405
opened May 24, 2024 by
MMuzzammil1
Fail to build tvm-unity from source on orin[Bug]
bug
Confirmed bugs
#2389
opened May 23, 2024 by
Louym
[Question] Single forward pass through ChatModule
question
Question about the usage
#2354
opened May 17, 2024 by
caenopy
Previous Next
ProTip!
Adding no:label will show everything without a label.