Yishuo Wang 300eb01d98 Add basic optimization for Qwen2.5 omni (#13022)		2025-03-28 17:21:52 +08:00
..
cli
ggml	LLM: add new qtype woq_int4 to support gemm int4 temporary. (#12706)	2025-01-15 14:41:33 +08:00
gptq
langchain
llamaindex
serving	Upgrade to vllm 0.6.2 (#12338)	2024-11-12 20:35:34 +08:00
transformers	Add basic optimization for Qwen2.5 omni (#13022)	2025-03-28 17:21:52 +08:00
utils	R1 Hybrid: Add Benchmark for DeepSeek R1 transformers example (#12854)	2025-02-19 18:33:21 +08:00
vllm	Fix qwen nan value issue on vllm (#12971)	2025-03-14 14:43:54 +08:00
__init__.py
convert_model.py
format.sh
llm_patching.py
models.py
optimize.py	initial implementation for low_bit_loader vLLM (#12838)	2025-02-19 19:45:34 +08:00