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
[Bug] Error while attempting to build PHI-3(128k) for use in MLC-LLM on the Orange Pi 5 Plus (RK3588)
bug
Confirmed bugs
#2307
opened May 9, 2024 by
mjsf12
[Bug] Compiling the MLC from source is failed
bug
Confirmed bugs
#2306
opened May 9, 2024 by
fengerhu1
[Bug] mlc-llm not working, tvm check returns none
bug
Confirmed bugs
#2301
opened May 9, 2024 by
CallMeTkt
[Bug] REST server doesn't work on V100 (SM70) - cudaErrorNoKernelImageForDevice (but chat works)
bug
Confirmed bugs
#2296
opened May 8, 2024 by
bayley
[Model Request] can we get Aryanne/Calypso-3B-alpha-v2-gguf
new-models
#2293
opened May 7, 2024 by
Louis654
Prebuilt StableLM 1.6B model compilation not working
bug
Confirmed bugs
#2283
opened May 6, 2024 by
saurav-pwh-old
[Bug] llama2 7b android compilation is giving "Can only handle constant size stack allocation for now" error
bug
Confirmed bugs
#2282
opened May 6, 2024 by
Ramees025
[Bug] Check failed: (args.size() == initial_indices_orig.size()) is false
bug
Confirmed bugs
#2276
opened May 5, 2024 by
jpf888
Phi-3 mini 4k instruct with MICROSOFT's quantization
help wanted
Looking for community help
new-models
#2273
opened May 4, 2024 by
federicoparra
[Question] Using FP8 quantization on a RedPajama-INCITE-Chat-3B-v1 model
question
Question about the usage
#2270
opened May 3, 2024 by
razetime
[Question] What models actually work with function calling?
question
Question about the usage
#2267
opened May 2, 2024 by
dtkettler
/opt/AI/llm_obj/mlc-llm/3rdparty/tvm/jvm/native/src/main/native/org_apache_tvm_native_c_api.cc:232:31: error: cannot initialize a parameter of type 'void **' with an rvalue of type 'JNIEnv **' (aka 'JNIEnv_ **') 232 | _jvm->AttachCurrentThread(&env, nullptr); | ^~~~ /usr/local/java/jdk-17.0.11/include/jni.h:1938:37: note: passing argument to parameter 'penv' here 1938 | jint AttachCurrentThread(void **penv, void *args) { | ^ /opt/AI/llm_obj/mlc-llm/3rdparty/tvm/jvm/native/src/main/native/org_apache_tvm_native_c_api.cc:309:31: error: cannot initialize a parameter of type 'void **' with an rvalue of type 'JNIEnv **' (aka 'JNIEnv_ **')
bug
Confirmed bugs
#2259
opened May 1, 2024 by
lbl1120
[Bug] Confirmed bugs
system-lib-prefix
would be cleared if device
is not strictly android
while mlc_llm compile
bug
#2255
opened Apr 30, 2024 by
BitCircuit
[Bug] Confirmed bugs
mlc_llm chat
throws errors for model mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
bug
#2254
opened Apr 30, 2024 by
BodhiHu
[Question] Omniquant. (AFAIK) scores best for Q. Methods, why no adoption? In any case, is per-tensor quant. best for Mixtral/MoE models?
question
Question about the usage
#2247
opened Apr 29, 2024 by
BuildBackBuehler
[Bug] TVMError: Check failed: (result) is false: Failed to allocate 99121664 bytes with alignment 16 bytes
bug
Confirmed bugs
#2243
opened Apr 28, 2024 by
zhjunqin
[Bug] Unexpected Error: The model weight size may be larger than GPU memory size
bug
Confirmed bugs
#2239
opened Apr 27, 2024 by
ahz-r3v
[Model Request] Microsoft Phi-3 mini Instruct (Faster and better then LLama 3 8B)
new-models
#2238
opened Apr 27, 2024 by
sebastienbo
2 tasks
[Bug] libc++abi: terminating due to uncaught exception of type tvm::runtime::InternalError: [14:02:26]
bug
Confirmed bugs
#2233
opened Apr 26, 2024 by
ash-rk
[Question] Support for Custom Attention Mask
question
Question about the usage
#2232
opened Apr 26, 2024 by
Peng-YM
Previous Next
ProTip!
Adding no:label will show everything without a label.