nvjullin f66673a39d

[Kernel] Added flashinfer fp8 per-tensor gemms (#22895) ...

Signed-off-by: Julien Lin <jullin@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2025-08-26 06:54:04 -07:00

..

piecewise

[torch.compile] Support conditional torch.compile per module (#22269)

2025-08-20 16:52:59 +00:00

__init__.py

…

backend.py

…

test_async_tp.py

…

test_basic_correctness.py

…

test_config.py

…

test_decorator.py

[torch.compile] Support conditional torch.compile per module (#22269)

2025-08-20 16:52:59 +00:00

test_full_graph.py

[Kernel/Quant] Remove the original marlin format and qqq (#23204)

2025-08-20 15:13:36 -04:00

test_functionalization.py

[NVIDIA][torch.compile] Support Flashinfer TRTLLM FP8-q/kv NVFP4-out Attention Kernel (#22703)

2025-08-22 22:09:05 +00:00

test_fusion_all_reduce.py

[CI Perf] Only test bfloat16 for tests/compile/test_fusion_all_reduce.py (#23132)

2025-08-19 20:18:52 -06:00

test_fusion_attn.py

[NVIDIA][torch.compile] Support Flashinfer TRTLLM FP8-q/kv NVFP4-out Attention Kernel (#22703)

2025-08-22 22:09:05 +00:00

test_fusion.py

[Kernel] Added flashinfer fp8 per-tensor gemms (#22895)

2025-08-26 06:54:04 -07:00

test_pass_manager.py

…

test_sequence_parallelism.py

[Kernel] Added flashinfer fp8 per-tensor gemms (#22895)

2025-08-26 06:54:04 -07:00

test_silu_mul_quant_fusion.py

[Kernel] Added flashinfer fp8 per-tensor gemms (#22895)

2025-08-26 06:54:04 -07:00

test_wrapper.py

…