Tyler Michael Smith eb5741ad42

[Kernel][Quantization] Integrate block-quantized CUTLASS kernels for DeepSeekV3 (#12587) ...

Integrates the block-quantized kernels introduced in
https://github.com/vllm-project/vllm/pull/11868 for use in linear
layers.

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>

2025-01-31 15:29:11 -08:00

..

aqlm

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

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

awq

[CI/Build] Suppress divide-by-zero and missing return statement warnings (#7001)

2024-08-05 16:00:01 -04:00

compressed_tensors

[MISC] Replace c10::optional with std::optional (#11730)

2025-01-05 10:20:34 +09:00

cutlass_w8a8

[Kernel][Quantization] Integrate block-quantized CUTLASS kernels for DeepSeekV3 (#12587)

2025-01-31 15:29:11 -08:00

fp8

[torch.compile] Dynamic fp8 + rms_norm fusion (#10906)

2024-12-13 03:19:23 +00:00

fused_kernels

[torch.compile] Dynamic fp8 + rms_norm fusion (#10906)

2024-12-13 03:19:23 +00:00

gguf

[AMD] Add support for GGUF quantization on ROCm (#10254)

2024-11-22 21:14:49 -08:00

gptq

[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047)

2024-06-09 16:23:30 -04:00

gptq_marlin

Update pre-commit hooks (#12475)

2025-01-27 17:23:08 -07:00

machete

[Kernel] Update cutlass_scaled_mm to support 2d group (blockwise) scaling (#11868)

2025-01-30 18:33:00 -08:00

marlin

Update pre-commit hooks (#12475)

2025-01-27 17:23:08 -07:00

vectorization.cuh

[torch.compile] Dynamic fp8 + rms_norm fusion (#10906)

2024-12-13 03:19:23 +00:00