yangzhuxinyzx 9c5660574b [Core] Share DFlash attention and norm boundaries across TP sizes (#1025) ...

* [Core] Share DFlash attention and norm boundaries across TP sizes

Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

* [Test] Validate installed TP2 and TP4 DFlash boundaries

Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

---------

Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

2026-10-07 15:10:21 +08:00

..

layers

[Kernel] Reduce DFlash2 scale and LM-head residency

2026-09-12 23:45:29 +08:00

model_loader

[Model Loader] Admit direct reads by storage and memory capacity

2026-10-03 08:07:30 +08:00

__init__.py

…

test_cpu_unquantized_gemm_dispatch.py

…

test_deepseek_v4_swa_rope.py

[Release] Restore public source snapshot to v1.3.0 (#329)

2026-08-26 15:18:10 +08:00

test_eagle_quantization.py

[Bugfix] Honor independent speculative draft load configuration

2026-10-05 00:44:42 +08:00

test_enabled_custom_ops.py

[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

2026-05-01 23:41:15 -04:00

test_ernie45_vl_mrope.py

…

test_flashinfer_autotune_cache.py

[UX] Add a persistent cache for FlashInfer autotuning (#42537)

2026-05-18 20:25:37 -07:00

test_gemma_hidden_act.py

[Models][Gemma3/Gemma4] Support hidden_act variants in gated MLP (#40588)

2026-05-08 11:29:11 -07:00

test_keye_mrope.py

[Model] Use mm_features for Keye-VL and Keye-1.5-VL M-RoPE (#39869)

2026-04-16 02:16:06 -07:00

test_keye_vl1_5_mrope.py

[Model] Use mm_features for Keye-VL and Keye-1.5-VL M-RoPE (#39869)

2026-04-16 02:16:06 -07:00

test_model_load_with_params.py

…

test_nemotron_h_quantization.py

Add LM head quantization support for ModelOpt (#42124)

2026-05-26 09:21:05 -07:00

test_oink_integration.py

[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

2026-05-01 23:41:15 -04:00

test_paddleocr_vl_mrope.py

[Model] Use mm_features to compute mrope positions for PaddleOCR-VL (#39888)

2026-04-16 06:14:00 -07:00

test_qwen3_5_quantization.py

[Kernel] Accelerate Qwen3.8 Flash Next decode on SM70

2026-08-28 01:01:55 +08:00

test_qwen3_omni.py

…

test_qwen3_vl_mrope.py

…

test_qwen35_gguf_collective_boundary.py

[Core] Share DFlash attention and norm boundaries across TP sizes (#1025)

2026-10-07 15:10:21 +08:00

test_routed_experts_capture.py

[RFC] Replace shared-memory routed experts with ModelRunnerOutput transfer and HTTP support (#39568)

2026-05-14 14:12:30 +00:00

test_sm70_fp8_qpn8_pp2_tp4.py

[Core] Move SM70 serialized FP8 dispatch into the linear kernel lifecycle

2026-10-03 03:36:20 +08:00

test_uva_tower_offload.py

[Release] Restore public source snapshot to v1.3.0 (#329)

2026-08-26 15:18:10 +08:00

test_weight_utils.py

…

test_weights_mapper_stacked.py

Merge remote-tracking branch 'onecat/main' into agent/v100-audit-pr341-glm53-20260828-010541

2026-08-28 01:23:46 +08:00