Harry Huangandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> c75cb63cd2 [Qwen4Exp] support Sequence Parallelism for Qwen3.8-Flash-Next (#56322) ...

Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-10-12 20:56:44 +08:00

..

test_activation.py

[ROCm] Use silu_and_mul_with_clamp's torch._C op (#52052)

2026-09-22 18:30:14 -05:00

test_apply_rotary_emb.py

[CI][Bugfix] Relax packed_qk_rope_ correctness test to one ULP (#59008)

2026-09-28 17:29:59 +00:00

test_batched_weight_rms_norm.py

[DFlash] Fuse precompute kv per-layer rmsnorms (#46761)

2026-06-25 19:32:07 -07:00

test_cpu_activation.py

[CPU][Perf]Added tanh AOR for faster gelu activations. (#44639)

2026-06-30 23:24:40 -07:00

test_fused_allreduce_gemma_rms_norm.py

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

test_fused_embed_norm.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_fused_q_kv_rmsnorm.py

[Bugfix][Quantization] Fix MXFP8 startup crash on layers below mm_mxfp8 shape limits (#54223)

2026-09-25 02:54:11 +00:00

test_fused_qk_norm_rope.py

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

test_fused_quant_layernorm.py

[CI][Bugfix] Extend groupwise rms_norm scale tolerance to CUDA (#58252)

2026-09-23 01:29:11 -07:00

test_fused_rms_norm_gated.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_fused_silu_mul_block_quant.py

[Bugfix] Fix int32 token offset overflow in fused SiLU block quant (#53409)

2026-08-28 16:23:36 -04:00

test_layernorm.py

[Test][ROCm] Account for gfx950 FP8 RMSNorm rounding (#49839)

2026-07-30 18:46:37 +08:00

test_minimax_reduce_rms.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_mrope.py

[Minimax-M3][Perf] Use triton_mrope for vision tower + int64 offset fix for triton_mrope (#58526)

2026-09-24 18:30:32 -07:00

test_opcheck.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_pos_encoding.py

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

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

test_rocm_aiter_ops.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_rocm_misc_ops.py

[ROCm][CI] Add ROCm misc ops and env tests (#53279)

2026-09-01 19:03:37 +00:00

test_rotary_embedding_mla_cache_fused.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_rotary_embedding.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_uva.py

[TEST][XPU][CI] Fix ci uva kernel test instability 2 (#60404)

2026-10-10 12:09:13 +08:00

test_vit_bilinear_pos_embed.py

[Perf] triton bilinear_pos_embed kernel for ViT (#37948)

2026-04-01 01:52:02 -07:00

test_vit_fp8_attn.py

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

test_vit_fp8_quant.py

[ROCm][CI] fix fp8 range in vit_fp8_quant (#46410)

2026-06-23 11:34:21 -05:00

test_vit_fp8_scaling.py

[MyPy][1/N] Fix mypy errors in some tests/ directories and enforce follow-imports=silent (#49570)

2026-07-30 05:02:51 -07:00

test_vocab_parallel_embedding.py

[Qwen4Exp] support Sequence Parallelism for Qwen3.8-Flash-Next (#56322)

2026-10-12 20:56:44 +08:00