Focusing
Block or Report
Block or report yzh119
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
apache/tvm Public
Open deep learning compiler stack for cpu, gpu and specialized accelerators
-
1,192 contributions in the last year
Less
More
Activity overview
Contributed to
uwsampl/SparseTIR,
uwsampl/sparsetir-artifact,
mlc-ai/mlc-llm
and 42 other
repositories
Contribution activity
June 2023
Created 15 commits in 6 repositories
Created a pull request in mlc-ai/package that received 1 comment
Support python 3.11 for CUDA
Python 3.11 is not enabled for manylinux prebuilt with GPU enabled. Also moves the wheel-building scripts from tlcpack to this folder for quick dev…
+360
−8
•
1
comment
Opened 10 other pull requests in 3 repositories
mlc-ai/mlc-llm
6
merged
2
closed
- [Doc] Update documentation
- [Doc] Tutorial on customizing conversation
- [Bugfix] Fix the behavior when SeparatorStyle is kLM
- [Bugfix] Fix the behavior when SeparatorStyle is LM
-
Customize
role_msg_sepandrole_empty_sepin Conversation Template. - [Bugfix] Fix the behavior when input is empty
- [Bugfix] Load models with bfloat16 dtype
- [Doc] Slight fix on documentation
tlc-pack/tlcpack
1
merged
apache/tvm
1
merged
Reviewed 13 pull requests in 4 repositories
mlc-ai/mlc-llm
6 pull requests
- [iOS] Handle invalid input URL
-
[Android] Fix compile error (#310) and
ndk-buildcannot reference - [FIX] Fix Crash when running Conversations without system prompts
- [Android] Vicuna 7B q4f16
- Model loading on shard level - GPT-NeoX, RWKV
- LLaMA family loading model on shard level - reducing memory usage
mlc-ai/relax
3 pull requests
apache/tvm
2 pull requests
mlc-ai/package
2 pull requests
1
contribution
in private repositories
Jun 6








