Woosuk KwonandGitHub 76a7983b23 [BugFix] Fix RoPE kernel on long sequences(#2164)

2023-12-17 17:09:10 -08:00

..

attention

Replace head_mapping params with num_kv_heads to attention kernel. (#1997)

2023-12-10 10:12:53 -08:00

quantization

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

activation_kernels.cu

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)

2023-12-07 23:16:52 -08:00

cache_kernels.cu

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)

2023-12-07 23:16:52 -08:00

cache.h

Avoid multiple redefinition (#1817)

2023-12-14 09:35:58 -08:00

cuda_compat.h

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)

2023-12-07 23:16:52 -08:00

cuda_utils_kernels.cu

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)

2023-12-07 23:16:52 -08:00

cuda_utils.h

Avoid multiple redefinition (#1817)

2023-12-14 09:35:58 -08:00

dispatch_utils.h

Avoid multiple redefinition (#1817)

2023-12-14 09:35:58 -08:00

layernorm_kernels.cu

[Optimization] Implement fused add rmsnorm (#1667)

2023-11-18 18:18:02 -08:00

ops.h

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

pos_encoding_kernels.cu

[BugFix] Fix RoPE kernel on long sequences(#2164)

2023-12-17 17:09:10 -08:00

pybind.cpp

Add GPTQ support (#916)

2023-12-15 03:04:22 -08:00

reduction_utils.cuh

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)

2023-12-07 23:16:52 -08:00