Robert Shaw c0c2335ce0

Integrate Marlin Kernels for Int4 GPTQ inference (#2497) ...

Co-authored-by: Robert Shaw <114415538+rib-2@users.noreply.github.com>
Co-authored-by: alexm <alexm@neuralmagic.com>

2024-03-01 12:47:51 -08:00

..

attention

Fix compile error when using rocm (#2648)

2024-02-01 09:35:09 -08:00

moe

Add fused top-K softmax kernel for MoE (#2769)

2024-02-05 17:38:02 -08:00

punica

Add LoRA support for Gemma (#3050)

2024-02-28 13:03:28 -08:00

quantization

Integrate Marlin Kernels for Int4 GPTQ inference (#2497)

2024-03-01 12:47:51 -08:00

activation_kernels.cu

Optimize GeGLU layer in Gemma (#2975)

2024-02-21 20:17:52 -08:00

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

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

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

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

Integrate Marlin Kernels for Int4 GPTQ inference (#2497)

2024-03-01 12:47:51 -08:00

pos_encoding_kernels.cu

[FIX] Support non-zero CUDA devices in custom kernels (#1959)

2024-01-02 19:09:59 -08:00

pybind.cpp

Integrate Marlin Kernels for Int4 GPTQ inference (#2497)

2024-03-01 12:47:51 -08:00

reduction_utils.cuh

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

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