zhrrr 61ab70ec3b [Model Runner V2] support mamba hybrid models align prefix cache (#42406) ...

Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>

2026-06-29 14:09:16 -07:00

..

attention

[ROCm] Fix AITER_UNIFIED_ATTN Dispatching After AITER Bump (#46780)

2026-06-26 02:09:56 -07:00

core

[ROCm][CI]Fix test_concat_and_cache_mla_rope_fused on ROCm (#46409)

2026-06-27 12:38:13 +08:00

helion

[Kernel][Helion][1/N] Add Helion kernel for fused_qk_norm_rope (#44010)

2026-06-29 22:54:15 +08:00

ir

[ROCm][CI] Fix ROCm LoRA Transformers fallback with full CUDA graphs (#41577)

2026-05-23 04:31:32 +00:00

mamba

[Model Runner V2] support mamba hybrid models align prefix cache (#42406)

2026-06-29 14:09:16 -07:00

moe

[CPU] Support cpu compressed-tensor w8a8 int8 moe (#42920)

2026-06-29 03:04:05 +00:00

quantization

[Hardware][AMD][CI] Fix Kernels Quantization test timeout (#46859)

2026-06-26 15:19:16 -05:00

__init__.py

…

allclose_default.py

…

quant_utils.py

…

test_apply_repetition_penalties.py

…

test_awq_int4_to_int8.py

[CPU] Bump up to the latest CPU kernels (#41924)

2026-05-07 05:45:59 -07:00

test_cache_kernels.py

…

test_compressor_kv_cache.py

[DSv4] Adding TRTLLM gen attention kernel (#43827)

2026-06-04 07:35:09 -07:00

test_concat_mla_q.py

…

test_cp_gather_fp8.py

…

test_fla_layernorm_guard.py

…

test_flex_attention.py

[FlexAttention] make custom mask mods fully cudagraphable (#45232)

2026-06-17 11:53:12 +08:00

test_fp32_router_gemm.py

[Model] Add MiniMax M3 support (#45381)

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

test_fused_deepseek_v4_qnorm_rope_kv_insert.py

[ROCm][CI] Relax fused layernorm quant test tolerances for one-ULP outliers (#46658)

2026-06-27 10:44:29 +08:00

test_fused_deepseek_v32_norm_rope.py

[GLM5] Implement op fusion for GLM5/DSV3.2 (#46876)

2026-06-28 08:17:39 -07:00

test_fused_gdn_post_conv.py

…

test_fused_indexer_q_rope_quant.py

[Model Refactoring] Move deepseek_v4_ops to models/deepseek_v4 [3/N] (#43073)

2026-05-19 00:52:54 -07:00

test_fused_inv_rope_fp8_quant.py

[Feat][DSV4] Fuse q pad into deepseek v4 fused kernel (#43162)

2026-05-26 05:12:54 -10:00

test_fused_minimax_m3_qknorm_rope_kv_insert.py

[Minimax-M3] BF16/FP8 Indexer using MSA (#45892)

2026-06-23 10:28:49 -07:00

test_fused_qk_norm_rope_gate.py

[Perf] fuse qk rmsnorm rope gate for qwen3.5 (#44176)

2026-06-09 22:12:17 +08:00

test_fused_quant_activation.py

…

test_fused_recurrent_packed_decode.py

…

test_fused_sigmoid_gating_delta_rule.py

…

test_kda.py

[Perf][KDA] Fuse gate softplus, chunk-local cumsum, and RCP_LN2 scaling (#43667)

2026-05-28 13:47:08 +00:00

test_mhc_kernels.py

[ROCm][DSV4] Disable TileLang MHC dispatch on gfx942 (#45931)

2026-06-22 09:26:54 +00:00

test_minimax_m3_amd_ops.py

[Model] Add MiniMax M3 support (#45381)

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

test_onednn.py

…

test_shuffle_rows.py

…

test_top_k_per_row.py

[Perf][DSv4/DSv3.2] Add cluster-cooperative topK kernel for low-latency scenarios (#43008)

2026-06-23 16:11:00 -07:00

utils.py

[ROCm][CI] Relax fused layernorm quant test tolerances for one-ULP outliers (#46658)

2026-06-27 10:44:29 +08:00