Comments (1)
tune_relax
isn't something we are currently using to tune LLMs, because it only supports static shape workloads. Instead we are using a mixed strategy that allows dynamic shape workloads as well. A tutorial should be coming soon :-)
from mlc-llm.
Related Issues (20)
- [Question] Rust SDK + WebAssembly + GPU? HOT 1
- [Bug] Failed to compile because the correct code page is not set
- [Bug] Token IDs not accepted by JSON grammar HOT 4
- [Question] Is GGUF model package format supported with quantized models? HOT 3
- [Question] Can I serve multiple models with the same instance?
- [Question] Is there an embeddings model in MLC format?
- [Question] Is Apple Silicon Neural Engine (ANE) and Core ML model package format supported? HOT 1
- [Model Request] OpenELM HOT 1
- [Question] Support for Custom Attention Mask
- [Bug] libc++abi: terminating due to uncaught exception of type tvm::runtime::InternalError: [14:02:26] HOT 3
- [Model Request] Microsoft Phi-3 mini Instruct (Faster and better then LLama 3 8B) HOT 2
- [Bug] Unexpected Error: The model weight size may be larger than GPU memory size HOT 5
- [Bug] TVMError: Check failed: (result) is false: Failed to allocate 99121664 bytes with alignment 16 bytes
- AutoTVM optimization? HOT 3
- Phi-3-3.8 billion model [Model Request] HOT 1
- [Question] Omniquant. (AFAIK) scores best for Q. Methods, why no adoption? In any case, is per-tensor quant. best for Mixtral/MoE models? HOT 1
- [Bug] Error: could not compile `regex-syntax`
- [Bug] `mlc_llm chat` throws errors for model `mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC`
- [Bug] `system-lib-prefix` would be cleared if `device` is not strictly `android` while `mlc_llm compile` HOT 2
- /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_ **') HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mlc-llm.