Gregory Shtrasberg 90eeea8f85

[Bugfix][ROCm] Fix for warp_size uses on host (#21205) ...

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>

2025-07-24 00:37:19 -07:00

..

dequantize.cuh

[Kernel] Add more dtype support for GGUF dequantization (#15879)

2025-04-02 01:58:48 -07:00

ggml-common.h

[Bugfix][kernels] Fix half2float conversion in gguf kernels (#15995)

2025-04-04 09:38:58 -07:00

gguf_kernel.cu

[Bugfix][ROCm] Fix for warp_size uses on host (#21205)

2025-07-24 00:37:19 -07:00

mmq.cuh

Fix CUDA kernel index data type in vllm/csrc/quantization/fused_kernels/layernorm_utils.cuh +10 (#15159)

2025-03-21 10:01:11 +08:00

mmvq.cuh

[Kernel] GGUF MMVQ kernel for multiple input vectors (#18754)

2025-06-16 17:33:26 +08:00

moe_vec.cuh

[Kernel] GGUF MoeVec kernel (#16780)

2025-05-06 23:07:23 -07:00

moe.cuh

[BugFix][ROCm] Fix GGUF MoE Dispatch Block_Dim for ROCm (#16247)

2025-04-08 05:10:26 -07:00

vecdotq.cuh

Missing comment explaining VDR variable in GGUF kernels (#13290)

2025-02-20 22:06:54 -08:00