5 people 867fd5e8ed [ROCm][Perf] Use flydsl moe with Minimax-M3 mxfp8 weights on gfx950 and implemented moe-backend selection (#46184) ...

Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Tan Pin Siang <tanpinsiang@gmail.com>

2026-06-27 10:22:57 +00:00

..

kernels

[CPU][RISC-V] Add RVV path for W4A8 INT4 GEMM (#45269)

2026-06-25 08:18:10 +00:00

layers

[ROCm][Perf] Use flydsl moe with Minimax-M3 mxfp8 weights on gfx950 and implemented moe-backend selection (#46184)

2026-06-27 10:22:57 +00:00

model_loader

Deprecate old FP8 online MoE quantization class (#44514)

2026-06-23 11:53:38 -07:00

models

[GLM5.2 Perf] fused_indexer_q_rope_quant triton kernel, 1.9% ~ 3.3% E2E Throughput improvement. (#46862)

2026-06-26 22:16:20 -07:00

offloader

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

warmup

Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477)

2026-06-22 11:54:14 -07:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

Add ability to replace oot ops when using lora (#37181)

2026-03-16 18:04:15 -07:00

parameter.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

utils.py

[Bugfix][Rocm]Aiter MoE re-uses existing tensor addresses after weight update. (#40390)

2026-05-06 10:32:26 +00:00