Driss Guessous e57e4d6e9e

Fix Broken macro for cutlass moe (#18049) ...

Signed-off-by: drisspg <drisspguessous@gmail.com>

2025-05-12 23:31:06 -07:00

..

aqlm

[Kernel] fix types used in aqlm and ggml kernels to support dynamo (#7596)

2024-08-16 14:00:11 -07:00

awq

[Kernel] Fix awq error when n is not divisable by 128 (#13227)

2025-02-13 20:07:05 -08:00

compressed_tensors

[ROCm]: Fix build from source failure with gcc14 and ROCm 6.3 (#13779)

2025-05-12 20:36:33 -07:00

cutlass_w8a8

Fix Broken macro for cutlass moe (#18049)

2025-05-12 23:31:06 -07:00

fp4

[Hardware/NVIDIA/Kernel] Enable nvidia/DeepSeek-R1-FP4 Model (#16362)

2025-05-09 16:24:41 -07:00

fp8

Removed unused marlin cuda code (#17684)

2025-05-06 17:59:47 -07:00

fused_kernels

[ROCm]: Fix build from source failure with gcc14 and ROCm 6.3 (#13779)

2025-05-12 20:36:33 -07:00

gguf

[Kernel] GGUF MoeVec kernel (#16780)

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

gptq

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

gptq_allspark

[Easy] Eliminate c10::optional usage in vllm/csrc (#17819)

2025-05-08 03:05:10 -07:00

gptq_marlin

[Kernel] fp4 marlin kernel (#17687)

2025-05-10 19:58:49 -07:00

machete

add cutlass support for blackwell fp8 gemm (#13798)

2025-03-04 07:55:07 -08:00

marlin

pre-commit autoupdate (#17380)

2025-04-29 06:46:55 -07:00

activation_kernels.cu

[torch.compile] Add torch inductor pass for fusing silu_and_mul with subsequent scaled_fp8_quant operations (#10867)

2025-05-01 07:59:28 -07:00

utils.cuh

[Feature][ROCm]Enable fusion pass for torch.compile on ROCm (#15050)

2025-03-31 04:42:18 -07:00

vectorization.cuh

dynamic distpatch of fp8 kernels (#14245)

2025-03-11 10:54:56 -04:00