Open Issues Need Help
View All on GitHub [transformers] support DeepSeek V3 14 days ago
enhancement good first issue help wanted huggingface feature
linkedin/Liger-Kernel linkedin/Liger-Kernel Efficient Triton Kernels for LLM Training
Open project →
6.5K
Efficient Triton Kernels for LLM Training
Python
#finetuning#gemma2#hacktoberfest#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels
DeepSeek Native Sparse Attention (NSA) Kernel 2 months ago
help wanted feature fun
linkedin/Liger-Kernel linkedin/Liger-Kernel Efficient Triton Kernels for LLM Training
Open project →
6.5K
Efficient Triton Kernels for LLM Training
Python
#finetuning#gemma2#hacktoberfest#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels
[feat] on-paper form of RoPE 3 months ago
enhancement good first issue feature
linkedin/Liger-Kernel linkedin/Liger-Kernel Efficient Triton Kernels for LLM Training
Open project →
6.5K
Efficient Triton Kernels for LLM Training
Python
#finetuning#gemma2#hacktoberfest#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels
TiledMLP 6 months ago
help wanted
linkedin/Liger-Kernel linkedin/Liger-Kernel Efficient Triton Kernels for LLM Training
Open project →
6.5K
Efficient Triton Kernels for LLM Training
Python
#finetuning#gemma2#hacktoberfest#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels
Transformers v5 compatibility 7 months ago
good first issue help wanted huggingface
linkedin/Liger-Kernel linkedin/Liger-Kernel Efficient Triton Kernels for LLM Training
Open project →
6.5K
Efficient Triton Kernels for LLM Training
Python
#finetuning#gemma2#hacktoberfest#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels
good first issue
linkedin/Liger-Kernel linkedin/Liger-Kernel Efficient Triton Kernels for LLM Training
Open project →
6.5K
Efficient Triton Kernels for LLM Training
Python
#finetuning#gemma2#hacktoberfest#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels
good first issue
linkedin/Liger-Kernel linkedin/Liger-Kernel Efficient Triton Kernels for LLM Training
Open project →
6.5K
Efficient Triton Kernels for LLM Training
Python
#finetuning#gemma2#hacktoberfest#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels
Add support for the SmolLM3 model. about 1 year ago
AI Summary: Add support for the SmolLM3 model to the Liger Kernel library by implementing necessary patching APIs and kernels to optimize its performance, similar to existing support for other LLMs like LLaMA and others. This involves adapting the existing framework to handle the specific architecture and operations of SmolLM3.
Complexity:
4/5
good first issue huggingface
linkedin/Liger-Kernel linkedin/Liger-Kernel Efficient Triton Kernels for LLM Training
Open project →
6.5K
Efficient Triton Kernels for LLM Training
Python
#finetuning#gemma2#hacktoberfest#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels