Divakar VermaandGitHub 1c1bb0bbf2 [Misc][MoE] add Deepseek-V3 moe tuning support (#12558) ...

Signed-off-by: Divakar Verma <divakar.verma@amd.com>

2025-01-30 00:47:30 +00:00

..

benchmark_aqlm.py

[Frontend] Add FlexibleArgumentParser to support both underscore and dash in names (#5718)

2024-06-20 17:00:13 -06:00

benchmark_layernorm.py

[Hardware] using current_platform.seed_everything (#9785)

2024-10-29 14:47:44 +00:00

benchmark_lora.py

[misc] Add LoRA kernel micro benchmarks (#11579)

2025-01-16 15:51:40 +00:00

benchmark_machete.py

[Model][Quantization] HQQ support through Marlin kernel expansion (#9766)

2024-11-19 13:31:12 -08:00

benchmark_marlin.py

[Model][Quantization] HQQ support through Marlin kernel expansion (#9766)

2024-11-19 13:31:12 -08:00

benchmark_moe.py

[Misc][MoE] add Deepseek-V3 moe tuning support (#12558)

2025-01-30 00:47:30 +00:00

benchmark_paged_attention.py

[FP8][Kernel] Dynamic kv cache scaling factors computation (#11906)

2025-01-23 18:04:03 +00:00

benchmark_quant.py

[Hardware] using current_platform.seed_everything (#9785)

2024-10-29 14:47:44 +00:00

benchmark_rmsnorm.py

[Misc] Kernel Benchmark for RMSNorm (#11241)

2024-12-17 06:57:02 +00:00

benchmark_rope.py

[Hardware] using current_platform.seed_everything (#9785)

2024-10-29 14:47:44 +00:00

benchmark_shapes.py

Add marlin unit tests and marlin benchmark script (#4815)

2024-05-16 09:36:49 -04:00

graph_machete_bench.py

[Kernel] Initial Machete W4A8 support + Refactors (#9855)

2024-11-18 12:59:29 -07:00

requirements.txt

[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701)

2024-09-23 13:46:26 -04:00

utils.py

[misc] Add LoRA kernel micro benchmarks (#11579)

2025-01-16 15:51:40 +00:00

weight_shapes.py

[Kernel] Initial Machete W4A8 support + Refactors (#9855)

2024-11-18 12:59:29 -07:00