vllm/csrc
2024-03-12 22:06:17 -07:00
..
attention [ROCM] Fix blockReduceSum to use correct warp counts for ROCm and CUDA (#3262) 2024-03-10 15:27:45 -07:00
moe Add fused top-K softmax kernel for MoE (#2769) 2024-02-05 17:38:02 -08:00
punica Enhance lora tests with more layer and rank variations (#3243) 2024-03-09 17:14:16 -08:00
quantization Integrate Marlin Kernels for Int4 GPTQ inference (#2497) 2024-03-01 12:47:51 -08:00
activation_kernels.cu Add kernel for GeGLU with approximate GELU (#3337) 2024-03-12 22:06:17 -07:00
cache_kernels.cu [Minor] Remove gather_cached_kv kernel (#3043) 2024-02-26 15:00:54 -08:00
cache.h [Minor] Remove gather_cached_kv kernel (#3043) 2024-02-26 15:00:54 -08:00
cuda_compat.h [ROCM] Fix blockReduceSum to use correct warp counts for ROCm and CUDA (#3262) 2024-03-10 15:27:45 -07:00
cuda_utils_kernels.cu [ROCm] add support to ROCm 6.0 and MI300 (#2274) 2024-01-26 12:41:10 -08:00
cuda_utils.h [ROCm] add support to ROCm 6.0 and MI300 (#2274) 2024-01-26 12:41:10 -08:00
custom_all_reduce_test.cu Implement custom all reduce kernels (#2192) 2024-01-27 12:46:35 -08:00
custom_all_reduce.cu Implement custom all reduce kernels (#2192) 2024-01-27 12:46:35 -08:00
custom_all_reduce.cuh No repeated IPC open (#2642) 2024-01-29 10:46:29 -08:00
dispatch_utils.h DeepseekMoE support with Fused MoE kernel (#2453) 2024-01-29 21:19:48 -08:00
layernorm_kernels.cu [FIX] Support non-zero CUDA devices in custom kernels (#1959) 2024-01-02 19:09:59 -08:00
moe_align_block_size_kernels.cu Fused MOE for Mixtral (#2542) 2024-01-29 22:43:37 -08:00
ops.h Add kernel for GeGLU with approximate GELU (#3337) 2024-03-12 22:06:17 -07:00
pos_encoding_kernels.cu [FIX] Support non-zero CUDA devices in custom kernels (#1959) 2024-01-02 19:09:59 -08:00
pybind.cpp Add kernel for GeGLU with approximate GELU (#3337) 2024-03-12 22:06:17 -07:00
reduction_utils.cuh [ROCm] Fix warp and lane calculation in blockReduceSum (#3321) 2024-03-11 13:14:07 -07:00