Yanming WandGitHub e0c6f556e8 [Build] Avoid building too many extensions (#1624)

2023-11-23 16:31:19 -08:00

..

attention

Fix integer overflows in attention & cache ops (#1514)

2023-10-31 15:19:30 -07:00

quantization

Support SqueezeLLM (#1326)

2023-10-21 23:14:59 -07:00

activation_kernels.cu

Support YaRN models (#1264)

2023-11-03 14:12:48 -07:00

cache_kernels.cu

Fix integer overflows in attention & cache ops (#1514)

2023-10-31 15:19:30 -07:00

cache.h

[Build] Avoid building too many extensions (#1624)

2023-11-23 16:31:19 -08:00

cuda_utils_kernels.cu

Allocate more shared memory to attention kernel (#1154)

2023-09-26 22:27:13 -07:00

cuda_utils.h

[Build] Avoid building too many extensions (#1624)

2023-11-23 16:31:19 -08:00

dispatch_utils.h

Avoid compiling kernels for double data type (#933)

2023-09-02 14:59:47 +09:00

layernorm_kernels.cu

[Optimization] Implement fused add rmsnorm (#1667)

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

ops.h

[Build] Avoid building too many extensions (#1624)

2023-11-23 16:31:19 -08:00

pos_encoding_kernels.cu

Support YaRN models (#1264)

2023-11-03 14:12:48 -07:00

pybind.cpp

[Build] Avoid building too many extensions (#1624)

2023-11-23 16:31:19 -08:00

reduction_utils.cuh

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00