Michael GoinandGitHub db5d0719e1 [Kernel] Add MXFP8 to Marlin GEMM/MoE and refactor Mxfp8LinearOp (#34664) ...

Signed-off-by: mgoin <mgoin64@gmail.com>

2026-04-01 09:41:42 -07:00

..

__init__.py

[CI/Build] Reorganize models tests (#17459)

2025-04-30 23:03:08 -07:00

test_awq.py

[Renderer] Define render_cmpl and render_chat (#34039)

2026-02-07 05:24:40 -08:00

test_bitsandbytes.py

[bnb] Skip moe + bnb test (#36896)

2026-03-12 18:03:25 +00:00

test_fp8.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00

test_gguf.py

[Bugfix][Quantization] Support BF16 tensors on GGUF (#29948)

2025-12-03 10:33:46 +00:00

test_gpt_oss.py

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

test_gptq_marlin.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_modelopt.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_mxfp4.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_mxfp8.py

[Kernel] Add MXFP8 to Marlin GEMM/MoE and refactor Mxfp8LinearOp (#34664)

2026-04-01 09:41:42 -07:00

test_nvfp4.py

[Kernel][Performance] Enable smaller Scaling Factor tiling for NVFP4 small-batch decoding (#30885)

2026-01-13 15:22:53 -08:00