Roberto L. Castroandvllm-agent a2ad4b74b9 [Perf] Enable DeepGEMM sparse MQA logits on the FP8 indexer cache, DSv4.1 (#62011) ...

Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: vllm-agent <claw@inferact.ai>

2026-10-27 19:25:19 +00:00

..

kernels

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

layers

[Perf] Enable DeepGEMM sparse MQA logits on the FP8 indexer cache, DSv4.1 (#62011)

2026-10-27 19:25:19 +00:00

model_loader

[Fast Start] Key the weight cache on MoE and linear kernel backends (#63506)

2026-10-26 04:06:24 +00:00

offloader

[Bugfix][Offloader] Preserve prefetch static-buffer slot ownership (#54975)

2026-09-07 10:58:44 +08:00

__init__.py

[CI/Build] Move test_utils.py to tests/utils.py (#4425)

2024-05-13 23:50:09 +09:00

test_attention_warmup.py

[Bugfix][MRV2] Fix FlashInfer attention and ReplaySSM warmups on MRV2 (#61013)

2026-10-11 16:04:41 -07:00

test_b12x_warmup.py

[Quantization] Add ModelOpt IQ2_XS, IQ2_XXS, and Q8_0 support via b12x (#59604)

2026-10-13 09:06:33 -07:00

test_bailing_mrope.py

[Model] Add Bailing V3 VL support (#55921)

2026-09-10 02:46:56 -07:00

test_cpu_unquantized_gemm_dispatch.py

[CPU] Conv1d optimised kernel for aarch64 (#54093)

2026-09-30 20:23:42 +08:00

test_deep_gemm_warmup.py

[MoE] Unify DeepGEMM MegaMoE experts behind one feature-matrix layer; add NVFP4 (#61538)

2026-10-15 19:02:01 +00:00

test_eagle_quantization.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_enabled_custom_ops.py

[ROCm][Perf] Route softmax MoE top-k, including fused shared-expert sigmoid, through AITER topk_gating (#56226)

2026-10-15 17:53:18 +00:00

test_ernie45_vl_mrope.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_flashinfer_autotune_warmup.py

[Fast Start] Add daemon-to-daemon warmup cache seeding for Preload (#63088)

2026-10-25 21:03:40 +08:00

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_jit_warmup_cutedsl_launcher.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_jit_warmup_triton_launcher.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_jit_warmup.py

[6/N][warmup][DSv4] Migrate sampling, and DFlash JIT kernels (#56323)

2026-09-12 17:24:24 -07:00

test_k2_horizon_rope_fold.py

[K2 Horizon] fold partial-RoPE permutation into q/k (and norm) weights (#55335)

2026-09-30 16:03:37 +08:00

test_keye_mrope.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_keye_vl1_5_mrope.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_mamba_triton_warmup.py

[Perf] Extend Qwen Triton warmup to avoid first-request latency spikes (#54797)

2026-09-07 11:46:00 +08:00

test_minicpmv4_7.py

[Model] Support MiniCPM-V 4.7 (#58674)

2026-10-11 10:21:10 +00:00

test_minicpmv.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_mistral_large_3_eagle.py

[Bugfix] Initialize missing attributes in mistral eagle (#45217)

2026-06-12 08:21:01 +08:00

test_model_load_with_params.py

Add pydocstyle to the ruff rules (#52136)

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

test_nemotron_h_quantization.py

[Perf][Kernel][Quantization] Fuse ReLU2 with static FP8 activation quantization (#53793)

2026-09-14 10:26:15 -07:00

test_oink_integration.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_paddleocr_vl_mrope.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_phi4mm_attention.py

[Security] Do not retain Phi-4 MM audio attention matrices (#60614)

2026-10-09 22:23:35 +08:00

test_plamo3.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_qwen3_5_quantization.py

Add LM head quantization support for ModelOpt (#42124)

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

test_qwen3_asr_mrope.py

[Rust Frontend][gRPC] Add audio and video media inputs (#53760)

2026-08-30 11:31:37 +08:00

test_qwen3_omni_mrope.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_qwen3_omni.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_qwen3_vl_mrope.py

[MyPy][4/N] Fix mypy errors in medium-hard tests/ dirs (#55485)

2026-10-20 04:51:15 -07:00

test_qwen_triton_warmup.py

[ROCm][Perf] Triton port of the fused GDN MTP decode kernel (#61855)

2026-10-23 10:41:07 +08:00

test_qwen_vl_triton_warmup.py

[Perf] Skip the M-RoPE warmup when every holder of the RoPE fuses it (#60246)

2026-10-10 06:47:39 +00:00

test_replayssm_warmup.py

[Mamba] Add FlashInfer ReplaySSM support for MTP (#52928)

2026-09-30 21:41:17 +00:00

test_routed_experts_capture.py

[MoE] Revert platform hook for routed-expert capture rows (#62624) (#63013)

2026-10-22 16:26:33 +08:00

test_sleep_mode_tensor_ownership.py

[Bugfix][Models] Register sleep-managed runtime buffers (#53507)

2026-08-29 10:32:24 +08:00

test_triton_dispatcher.py

[Bugfix] Forward launch grid to Triton kernel overrides (#63999)

2026-10-27 14:46:07 +00:00

test_utils.py

[Perf] Drop BasevLLMParameter's Python __torch_function__ (#63785)

2026-10-27 15:30:25 +01:00

test_watermark_sample_warmup.py

[watermarking] Dual-key gumbel-max watermarking for speculative decoding support (#56122)

2026-09-12 18:42:01 +00:00

test_weight_utils.py

[Bugfix][RL] Load attention sinks through weight_loader for layerwise reload (#57797)

2026-10-14 10:17:58 +00:00