Kunshang Ji 53ec16a705 [Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145) ...

Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

2026-03-12 07:57:47 -07:00

..

cpu

…

deepgemm

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

bench_concat_mla_q.py

[Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA query concat - DeepSeek-V3.2 (#34917)

2026-03-09 09:50:36 -07:00

bench_cp_gather_fp8.py

[Attention][Perf] Optimize cp_gather_and_upconvert_fp8_kv_cache - DeepSeek-v3.2 (#35290)

2026-03-09 09:46:57 -07:00

benchmark_2d_silu_mul_fp8_quant.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00

benchmark_activation.py

…

benchmark_block_fp8_gemm.py

…

benchmark_cutlass_moe_fp8.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

benchmark_cutlass_moe_nvfp4.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_device_communicators.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

benchmark_fp8_gemm.py

…

benchmark_fused_collective.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

benchmark_fused_topk.py

…

benchmark_grouped_gemm_cutlass.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

benchmark_int8_gemm.py

…

benchmark_layernorm.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_lora.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_machete.py

…

benchmark_marlin.py

…

benchmark_mla_k_concat.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_moe_align_block_size.py

…

benchmark_moe_defaults.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_moe_permute_unpermute.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_moe.py

replace with torch.cuda.device with with torch.accelerator.device_index (#36144)

2026-03-11 23:12:57 -07:00

benchmark_mrope.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_mxfp4_qutlass.py

…

benchmark_nvfp4_gemm.py

…

benchmark_nvfp4_quant.py

…

benchmark_nvfp4_qutlass.py

…

benchmark_paged_attention.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_per_token_group_quant.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_per_token_quant_fp8.py

…

benchmark_quant.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_reshape_and_cache_flash.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_reshape_and_cache.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_rmsnorm.py

…

benchmark_rope.py

…

benchmark_shapes.py

…

benchmark_silu_mul_fp8_quant.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_trtllm_decode_attention.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_trtllm_prefill_attention.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

benchmark_w8a8_block_fp8.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

graph_machete_bench.py

…

requirements.txt

…

utils.py

…

weight_shapes.py

…