3 people de69e821b7 [ROCm][Perf][DeepSeek V4] Fuse native FP8 shared expert with MXFP4 routed experts (#53161) ...

Signed-off-by: fai <fangzhouai@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Cursor Agent <agent@cursor.com>

2026-09-06 19:42:21 -07:00

..

test_fused_shared_expert.py

[ROCm][Perf][DeepSeek V4] Fuse native FP8 shared expert with MXFP4 routed experts (#53161)

2026-09-06 19:42:21 -07:00

test_mla_short_prefill_indexer.py

[Attention] Enable masked MHA for GLM-5 head dimensions (#53785)

2026-08-27 21:17:12 +00:00

test_pooler_activations.py

[Misc] Replace assert with proper exceptions for security and validation in pooling (#43286)

2026-05-22 18:43:33 +08:00

test_pooler_heads.py

[Misc] Add unit tests for pooler head classes (#44471)

2026-06-04 17:59:25 +00:00

test_pooler_methods.py

[Pooling] Improve BGE-M3 sync pooling throughput by up to 3.13% (#53464)

2026-08-24 08:33:32 -04:00

test_rocm_unquantized_gemm.py

[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907)

2026-08-11 14:19:16 -04:00