| Twelve Attempts at an FP4 Kernel |
sources/blogs/amandeep-nvfp4-attempts.md |
| Colfax Article Source Kernels |
sources/blogs/colfax-article-source-kernels.md |
| Colfax CUTLASS Tutorial: GEMM Kernels Using Tensor Memory for Blackwell |
sources/blogs/colfax-cutlass-blackwell.md |
| Colfax CUTLASS Kernels |
sources/blogs/colfax-cutlass-kernels.md |
| DeepGEMM tensor-core kernel library |
sources/blogs/deepgemm.md |
| FlashAttention-4 Blog |
sources/blogs/flash-attention-4.md |
| FlashMLA upstream README |
sources/blogs/flashmla.md |
| Anatomy of a Reward Hack |
sources/blogs/gpu-mode-reward-hack.md |
| Writing High-Performance Matrix Multiplication Kernels for Blackwell with JAX Pallas |
sources/blogs/jax-pallas-blackwell-matmul.md |
| Modular: Matrix Multiplication on Blackwell, Part 3 |
sources/blogs/modular-blackwell-matmul.md |
| NVIDIA Developer Code Samples |
sources/blogs/nvidia-code-samples.md |
| NVIDIA Qwen3-Next Architecture Announcement |
sources/blogs/qwen3-next-architecture.md |
| NVFP4 GEMV |
sources/blogs/simon-nvfp4-gemv.md |
| simveit effective_transpose |
sources/blogs/simveit-effective-transpose.md |
| simveit load_and_store |
sources/blogs/simveit-load-and-store.md |
| tcgen05 for dummies |
sources/blogs/tcgen05-tutorial.md |
| TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell |
sources/blogs/tflops-gap-fp4-moe.md |
| Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation |
sources/blogs/tilus-nvidia.md |
| DeepSeek-V3.2-Exp in vLLM: Fine-Grained Sparse Attention in Action |
sources/blogs/vllm-deepseek-v3-sparse-attention.md |
| Blackwell NVFP4 Kernel Hackathon Journey |
sources/blogs/yue-nvfp4-hackathon.md |
| FlashInfer MLSys 2026 - Track A: Fused MoE FP8 |
sources/contests/flashinfer-mlsys26/track-a-fused-moe.md |
| FlashInfer MLSys 2026 - Track B: Sparse Attention |
sources/contests/flashinfer-mlsys26/track-b-sparse-attention.md |
| FlashInfer MLSys 2026 - Track C: Gated Delta Net |
sources/contests/flashinfer-mlsys26/track-c-gated-delta-net.md |
| GPU Mode NVFP4 Hackathon - Problem 1: Batched GEMV |
sources/contests/gpu-mode-nvfp4/problem-1-gemv.md |
| GPU Mode NVFP4 Hackathon - Problem 2: NVFP4 GEMM |
sources/contests/gpu-mode-nvfp4/problem-2-gemm.md |
| GPU Mode NVFP4 Hackathon - Problem 3: Gated Dual GEMM |
sources/contests/gpu-mode-nvfp4/problem-3-gated-dual-gemm.md |
| GPU Mode NVFP4 Hackathon - Problem 4: Grouped GEMM |
sources/contests/gpu-mode-nvfp4/problem-4-grouped-gemm.md |
| NVIDIA Blackwell Compatibility Guide |
sources/docs/blackwell-compatibility-guide.md |
| Microbenchmarking NVIDIA's Blackwell Architecture |
sources/docs/blackwell-microbenchmarking.md |
| CUDA Programming Guide: Programmatic Dependent Launch |
sources/docs/cuda-programming-guide-pdl.md |
| cuTile Python Documentation |
sources/docs/cutile-python-dsl.md |
| CUTLASS Changelog: SM100/Blackwell Entries |
sources/docs/cutlass-changelog-sm100.md |
| CUTLASS Blackwell Cluster Launch Control |
sources/docs/cutlass-clc-documentation.md |
| CUTLASS CuTe DSL Documentation |
sources/docs/cutlass-cute-dsl.md |
| FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling |
sources/docs/flash-attention-4.md |
| K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model |
sources/docs/k-search-kernel-generation.md |
| NVIDIA Blackwell Tuning Guide |
sources/docs/nvidia-blackwell-tuning-guide.md |
| NVIDIA CUTLASS Blackwell support map |
sources/docs/nvidia-cutlass-blackwell.md |
| PTX ISA Fifth-Generation Tensor Core and CLC Reference |
sources/docs/nvidia-ptx-isa-sm100.md |
| Triton 3.6 Release Notes — Blackwell Backend Work |
sources/docs/triton-3.6-blackwell.md |
| Fix multicast bug and optimize masked GEMM |
sources/prs/DeepGEMM/PR-193.md |
| [Public release 26/04] Introducing Mega MoE, FP4 Indexer and other features/fixes |
sources/prs/DeepGEMM/PR-304.md |
| Sync nv_dev with upstream #316 (Mega MoE optimizations & benchmarks) |
sources/prs/DeepGEMM/PR-328.md |
| [None][feat] sm100 weight-only kernel |
sources/prs/TensorRT-LLM/PR-10190.md |
| [TRTLLM-9831][perf] Enable 2CTA with autotune for CuteDSL MoE and Grouped GEMM optimizations |
sources/prs/TensorRT-LLM/PR-10201.md |
| [TRTLLM-10276][feat] Integrate cutedsl argmax kernel |
sources/prs/TensorRT-LLM/PR-10476.md |
| [None] [feat] Add densegemm backend for MoE |
sources/prs/TensorRT-LLM/PR-10479.md |
| [https://nvbugs/5799917][fix] Recover from CUTLASS MoE doActivation perf regression for MXFP4/NVFP4 dtype |
sources/prs/TensorRT-LLM/PR-11165.md |
| [None][feat] Optimize super-v3 nvfp4 for better perf |
sources/prs/TensorRT-LLM/PR-11273.md |
| [None][feat] Optimize by fuse nvfp4_quant to layernorm_gated for mamba2_mixer |
sources/prs/TensorRT-LLM/PR-11473.md |
| [TRTLLM-11092][feat] add support for visual gen FA4 attention backend |
sources/prs/TensorRT-LLM/PR-11697.md |
| [TRTLLM-11119][feat] Blackwell SageAttention, Integrate into AttentionOp API |
sources/prs/TensorRT-LLM/PR-11718.md |
| [None][feat] Add fused DiT QK Norm + RoPE CUDA kernel for FLUX |
sources/prs/TensorRT-LLM/PR-11869.md |
| [TRTLLM-10990][feat] Fuse SwiGLU and quant into shared expert |
sources/prs/TensorRT-LLM/PR-11897.md |
| [TRTLLM-10407][feat] Integrate CuTE DSL top-k kernel for Blackwell |
sources/prs/TensorRT-LLM/PR-11900.md |
| [TRTLLM-11289][feat] Integrate CuteDSL's bf16 dense GEMMs |
sources/prs/TensorRT-LLM/PR-12074.md |
| [None][feat] CuteDSL MOE: Add raster along M/N support for blockscaled contiguous backbone kernel |
sources/prs/TensorRT-LLM/PR-12079.md |
| [None][feat] Add DWDP (Distributed Weight Data Parallelism) support for MoE inference |
sources/prs/TensorRT-LLM/PR-12136.md |
| [None][feat] Support update weight for nvfp4 |
sources/prs/TensorRT-LLM/PR-12320.md |
| [https://nvbugs/5983390][perf] Kernel fusions in _gather_k_cache_for_chunk of Indexer in DSA |
sources/prs/TensorRT-LLM/PR-12322.md |
| [TRTLLM-10407][perf] Add cute dsl single pass multi cta cluster topk |
sources/prs/TensorRT-LLM/PR-12354.md |
| [None][feat] Temporally-Correlated Heuristic-guided Indexer TopK for Sparse Attention |
sources/prs/TensorRT-LLM/PR-12385.md |
| [None][feat] Trtllm-gen FMHA JIT support |
sources/prs/TensorRT-LLM/PR-12612.md |
| [None][feat] Add triton paged attention for AutoDeploy |
sources/prs/TensorRT-LLM/PR-12642.md |
| [TRTLLM-11585][feat] Add CUTEDSL moe backend for nemotron-h |
sources/prs/TensorRT-LLM/PR-12884.md |
| [TRTLLM-11485][feat] Feature rework: Add SageAttention refreshed kernels (attentionOp only) |
sources/prs/TensorRT-LLM/PR-12937.md |
| [#12716][feat] Fused cross-head QK Norm + RoPE kernel for WAN |
sources/prs/TensorRT-LLM/PR-13052.md |
| [None][feat] Add FP4 residual quantization kernel without channel reo… |
sources/prs/TensorRT-LLM/PR-13117.md |
| [TRTLLM-34871][feat] Add cute dsl FP8 paged MQA logits decode kernel |
sources/prs/TensorRT-LLM/PR-13219.md |
| [None][feat] Integrate FP4 indexer for DSA on Blackwell |
sources/prs/TensorRT-LLM/PR-13340.md |
| [None][perf] Scheme X L2-aware dispatcher and PDL launchers for sparse-attention GVR Top-K |
sources/prs/TensorRT-LLM/PR-13477.md |
| [None][feat] Fuse FP8 1x128 quantize + UE8M0 scale pack on SM100 |
sources/prs/TensorRT-LLM/PR-13628.md |
| [https://nvbugs/6108841][fix] add hidden_dim=6144 router GEMM instantiation for GLM-5 |
sources/prs/TensorRT-LLM/PR-13740.md |
| [None][fix] Plumb swiglu_limit through DeepGEMM and TRTLLMGen FP8 fused MoE |
sources/prs/TensorRT-LLM/PR-13767.md |
| [None][fix] Fix fused MHC for DeepSeek-V4-Pro hidden size |
sources/prs/TensorRT-LLM/PR-13771.md |
| [None][feat] Indexer topk opt |
sources/prs/TensorRT-LLM/PR-13811.md |
| [None][perf] FC2 DenseGEMM autotune: split-K, swap_ab, fine-grained tuning buckets |
sources/prs/TensorRT-LLM/PR-13833.md |
| [None][perf] mHC fused_hc kernel optimizations + DS-V4 entry-boundary RMSNorm fold-in |
sources/prs/TensorRT-LLM/PR-13892.md |
| [TRTLLM-35237][feat] Add cute dsl FP4 paged MQA logits decode kernel |
sources/prs/TensorRT-LLM/PR-13929.md |
| [None][feat] Keep DSv4 o_a_proj as FP8, and port vLLM's fused_inv_rope_fp8_quant |
sources/prs/TensorRT-LLM/PR-13938.md |
| [None][feat] Add chunked prefill support for Gemma4 (text + vision multimodal) |
sources/prs/TensorRT-LLM/PR-14134.md |
| [None][feat] Update the logic of FMHA JIT path |
sources/prs/TensorRT-LLM/PR-14291.md |
| feat: Add w4a8_mxfp4_fp8 quantization recipe. |
sources/prs/TensorRT-LLM/PR-4867.md |
| [None][chore] Fix kernel launch param and add TRTLLM MoE backend test |
sources/prs/TensorRT-LLM/PR-7524.md |
| [None][fix] Fix and add test for TRTLLM MoE backend |
sources/prs/TensorRT-LLM/PR-7755.md |
| [TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache |
sources/prs/TensorRT-LLM/PR-8405.md |
| [TRTLLM-9685] [feat] Add gather fc1 kernel by cuteDSL |
sources/prs/TensorRT-LLM/PR-9618.md |
| [None][feat] Adding torch ext API for FusedAddRMSNormQuant kernel |
sources/prs/TensorRT-LLM/PR-9905.md |
| Add b200 tunings for scan.exclusive.sum |
sources/prs/cccl/PR-3559.md |
| Fix SM100 histogram tunings |
sources/prs/cccl/PR-3691.md |
| Add nondeterministic reduce that uses atomics |
sources/prs/cccl/PR-4961.md |
Combine block_reduce_warp_reduction_nondeterministic.cuh specialization with original deterministic one |
sources/prs/cccl/PR-5408.md |
| Integrate decoupled lookahead warpspeed scan |
sources/prs/cccl/PR-6811.md |
Radix-selection based BlockTopK specialization |
sources/prs/cccl/PR-7384.md |
Implement the new tuning API for DeviceRleDispatch |
sources/prs/cccl/PR-7669.md |
Optimized Device-to-Device Tensor Copy (cudax) |
sources/prs/cccl/PR-7823.md |
| Avoid passing uninitialized values to scan_op |
sources/prs/cccl/PR-8184.md |
| [Port `thrust::min |
max_element` to CUB](../sources/prs/cccl/PR-8291.md) |
Implement the new tuning API for DispatchSelectIf |
sources/prs/cccl/PR-8311.md |
| simplify dispatch segmented reduce to use latest dispatch and new tunings API |
sources/prs/cccl/PR-8332.md |
| Apply some random warpspeed tunings |
sources/prs/cccl/PR-8352.md |
| Vectorize mbarrier initialization in warpspeed scan |
sources/prs/cccl/PR-8423.md |
| Blockwise and Groupwise GEMM for Blackwell and Improvements for Hopper |
sources/prs/cutlass/PR-2139.md |
| Blockwise Improvement and Programmatic Dependent Launch |
sources/prs/cutlass/PR-2161.md |
| [ex77] fix mla split; add fwd lse; add bwd varlen |
sources/prs/cutlass/PR-2366.md |
| Example 77 add blackwell fmha bwd for MLA shape |
sources/prs/cutlass/PR-2466.md |
| Add Blackwell MLA forward (shape: d=192, dv=128) implementation |
sources/prs/cutlass/PR-2472.md |
| fix: examples/cute/tutorial/blackwell/04_mma_tma_2sm_sm100.cu GridDim miscalculated |
sources/prs/cutlass/PR-2492.md |
| DistGEMM bug fixes |
sources/prs/cutlass/PR-2713.md |
| Support for GEMM-K=0 for Blackwell Grouped GEMMs |
sources/prs/cutlass/PR-2746.md |
| Blockscaled Ragged Contiguous Grouped Gemm for MoEs |
sources/prs/cutlass/PR-2790.md |
| [Bug Fix]Bypass launch grids for SM120 Kernel with SM90 Mainloop & SM100 TileScheduler |
sources/prs/cutlass/PR-2865.md |
| Fix incorrect tensor layout strides in Blackwell MMA tutorial comments |
sources/prs/cutlass/PR-2921.md |
| [CuTeDSL] Fix: SM100 block-scale gemm overlapping accumulator |
sources/prs/cutlass/PR-2995.md |
| [Cute,Fwd,Sm100] Implement SplitKV |
sources/prs/flash-attention/PR-1940.md |
| Blackwell FlashAttention-BWD (v1.0) |
sources/prs/flash-attention/PR-1945.md |
| [Cute] Block sparse support Sm100 |
sources/prs/flash-attention/PR-1985.md |
| [Cute,Fwd,Sm100] Support paged attention |
sources/prs/flash-attention/PR-1999.md |
| [Cute,Sm100,Fwd] use correction warps for epi when not using TMA |
sources/prs/flash-attention/PR-2014.md |
| [Cute,Bwd,Sm100] enable deterministic mode for sm100 bwd and fix race conditions |
sources/prs/flash-attention/PR-2033.md |
| [Cute,Fwd] Extend score_mod to variable sequence length |
sources/prs/flash-attention/PR-2043.md |
| Add score-mod bwd support |
sources/prs/flash-attention/PR-2070.md |
| Add blocksparse support for bwd on blackwell |
sources/prs/flash-attention/PR-2085.md |
| [Cute,Fwd,Sm100] distributed offset calculation for paged KV |
sources/prs/flash-attention/PR-2104.md |
| [Cute,Fwd,Sm100] fp8 e4m3 and e5m2 support |
sources/prs/flash-attention/PR-2109.md |
| [Cute,Fwd,Sm100] support irregular qhead / kvhead ratios |
sources/prs/flash-attention/PR-2186.md |
| [Ai-assisted] CLC work stealing |
sources/prs/flash-attention/PR-2218.md |
| [Fwd,Sm90] Add paged KV attention support (tma and cp.async) |
sources/prs/flash-attention/PR-2360.md |
| Feat([FA4][CUTE DSL]) Add head_dim=256 support (forward + backward) |
sources/prs/flash-attention/PR-2412.md |
| [Cute,Sm100,Fwd] add MLA 64/512 with topk sparsity for MQA 128 heads |
sources/prs/flash-attention/PR-2441.md |
| [hd256] Improve forward kernel with exp2 FMA emulation (3% to 9% performance gain) |
sources/prs/flash-attention/PR-2488.md |
| [hd256] Add TMA paged KV support to SM100 2CTA forward kernel |
sources/prs/flash-attention/PR-2489.md |
| [FA4][hd256] Backward TMA bulk-store epilogue + LSE/dpsum coalesce |
sources/prs/flash-attention/PR-2497.md |
| [nvidia] initial support for blackwell kernels |
sources/prs/flashinfer/PR-1039.md |
| bugfix: adding lse output to blackwell fmha kernels |
sources/prs/flashinfer/PR-1071.md |
| bugfix: follow user-specified sm_scale for blackwell cutlass fmha |
sources/prs/flashinfer/PR-1072.md |
| perf: accelerate blackwell grouped gemm |
sources/prs/flashinfer/PR-1086.md |
| bugfix: host-precomuted plan function for blackwell fmha |
sources/prs/flashinfer/PR-1106.md |
| Add CUTLASS fused moe kernels from TensorRT-LLM. |
sources/prs/flashinfer/PR-1113.md |
| hotfix: fix the blackwell fmha stream |
sources/prs/flashinfer/PR-1116.md |
| Add more logging to TRTLLM-GEN debug trace (NFC) |
sources/prs/flashinfer/PR-1158.md |
| bugfix: fix blackwell fmha hanging issue for empty kv_len |
sources/prs/flashinfer/PR-1198.md |
| feat: trtllm-gen fp8 moe kernels |
sources/prs/flashinfer/PR-1212.md |
| Feature/sm100 low latency nvfp4 kernels |
sources/prs/flashinfer/PR-1214.md |
| Fix missing hash in the cudnn cubin path |
sources/prs/flashinfer/PR-1227.md |
| feat: Add non-causal cudnn prefill kernels |
sources/prs/flashinfer/PR-1230.md |
| feat: Support MXFP8 x MXFP4 CUTLASS grouped GEMM |
sources/prs/flashinfer/PR-1241.md |
| Reduce the JIT compilation time of gen_gemm_sm100_module |
sources/prs/flashinfer/PR-1251.md |
| refactor: refactor trtllm-gen attention kernel integration code |
sources/prs/flashinfer/PR-1289.md |
| Update cutlass fp4 moe kernels |
sources/prs/flashinfer/PR-1294.md |
| add cutlass backend for mm_fp4 |
sources/prs/flashinfer/PR-1296.md |
| Add blockwise-scaled FP8 GEMM via TRTLLM-Gen. |
sources/prs/flashinfer/PR-1320.md |
| gpt-oss: Add MXFP8 x MXFP4 CUTLASS MOE for SM100 and BF16 x MXFP4 CUTLASS for SM90 + SwigluBias Activation |
sources/prs/flashinfer/PR-1396.md |
| feature: add cutlass as bmm_fp8 backend. |
sources/prs/flashinfer/PR-1397.md |
| fix shared memory alignment conflict in sampling.cuh |
sources/prs/flashinfer/PR-1402.md |
| Remove getEnvEnablePDL in favor of enable_pdl parameter |
sources/prs/flashinfer/PR-1446.md |
| tuner: Trtllm-gen Fp4 MoE Autotunner |
sources/prs/flashinfer/PR-1475.md |
| refactor fp4 masked gemm cute-dsl implementation and add manual cache |
sources/prs/flashinfer/PR-1521.md |
| feat: Integrate TRTLLM varlen kernel for deepseek R1 prefill |
sources/prs/flashinfer/PR-1537.md |
| fix: separate out fp4 lib into sm90 and sm100 versions, add oob checking in fused moe |
sources/prs/flashinfer/PR-1565.md |
| feat: initial support for SM103, SM110, SM120, SM121 |
sources/prs/flashinfer/PR-1608.md |
| feat: cutlass fp4 gemm bringup for SM120 & SM121 |
sources/prs/flashinfer/PR-1609.md |
| bugfix: trtllm-gen fmha sm101 and sm100 compatibility |
sources/prs/flashinfer/PR-1631.md |
| TGV GEMM as a BF16 backend alternative to cuBLAS |
sources/prs/flashinfer/PR-1668.md |
| bugfix: partially fix tests/test_trtllm_gen_fused_moe.py unit test failure |
sources/prs/flashinfer/PR-1724.md |
| TVM: support TVM binding for GroupedGemm |
sources/prs/flashinfer/PR-1725.md |
| feat: trtrllm-gen global scaled FP8 GEMMs |
sources/prs/flashinfer/PR-1829.md |
| Add head_dim=64 for blackwell cutlass fmha implementation |
sources/prs/flashinfer/PR-1850.md |
| Tune kernel compilation parameters for https://github.com/flashinfer-ai/flashinfer/pull/1850 |
sources/prs/flashinfer/PR-1878.md |
| feat: Add FP4 TRTLLM-Gen throughput MOE batched gemms |
sources/prs/flashinfer/PR-1882.md |
| Feature: Support Relu2 activation in fused MoE |
sources/prs/flashinfer/PR-1954.md |
| [DSV3] Optimized Router Gemm |
sources/prs/flashinfer/PR-2019.md |
| update trtllm cutlass moe |
sources/prs/flashinfer/PR-2020.md |
| [NVIDIA] Thor & Spark Support |
sources/prs/flashinfer/PR-2028.md |
| feat: Add flashinfer.rope.rope_quantize_fp8_append_paged_kv_cache (fused RoPE + Q + KV cache, supports MLA/GQA/MHA) |
sources/prs/flashinfer/PR-2037.md |
| Rebase FP8 SM100 Cutlass FMHA Attention to main (original PR#1238) |
sources/prs/flashinfer/PR-2047.md |
| perf: Optimize helper max/minmax function in sampling.cuh |
sources/prs/flashinfer/PR-2058.md |
| feat: BF16 GEMM using CUTLASS backend for SM100 |
sources/prs/flashinfer/PR-2070.md |
| feat: add trtllm-gen per-tensor sparseMla kernels. |
sources/prs/flashinfer/PR-2138.md |
| feat: further optimize top-k and add fused top-k page construction kernels for DSA |
sources/prs/flashinfer/PR-2215.md |
| feat: Fused RMSNorm + FP4 Quantization Kernels in CuTe-DSL |
sources/prs/flashinfer/PR-2233.md |
| Remove cudaStreamSynchronize from gemm_groupwise_sm120.cuh for CUDA graph compatibility |
sources/prs/flashinfer/PR-2244.md |
| fix: Add global scale support and optional output allocation for RMSNorm+FP4Quant fusion kernels |
sources/prs/flashinfer/PR-2260.md |
| [TRTLLM-Gen Fmha] add optimized trtllm-gen decode kernels for high throughput + speculative decoding |
sources/prs/flashinfer/PR-2265.md |
| [Perf][Feature] Add SM103-specific schedulers for NVFP4 CUTLASS kernels |
sources/prs/flashinfer/PR-2303.md |
| [ML3] Optimized Router Gemm |
sources/prs/flashinfer/PR-2323.md |
| [perf] Improve gemm_fp8_nt_groupwise (cutlass backend) by 10-40% for batch sizes <= 32 |
sources/prs/flashinfer/PR-2327.md |
| Optimize quantization function in large problem size |
sources/prs/flashinfer/PR-2343.md |
| Enable fp16/bf16/f32 support for selective_state_update (mamba) |
sources/prs/flashinfer/PR-2366.md |
| feat: [Qwen3-Next] Add Cute DSL GDN decode kernel and tests |
sources/prs/flashinfer/PR-2370.md |
| A Blackwell-optimized version of selective_state_update (mamba) |
sources/prs/flashinfer/PR-2387.md |
| feat: cuteDSL fp4 moe for better DSR1 performance. |
sources/prs/flashinfer/PR-2398.md |
| perf: improve gdn decode cute-dsl kernels |
sources/prs/flashinfer/PR-2405.md |
| refactor: simplify fp4 rmsnorm |
sources/prs/flashinfer/PR-2421.md |
| refactor: refactoring cuda code to cute-dsl (part 1) |
sources/prs/flashinfer/PR-2428.md |
| fix: Fix NaN output in mxfp8_quantize for very small input values |
sources/prs/flashinfer/PR-2441.md |
| Add cute-dsl backends to mxfp[8,4]_quantization for future refactor |
sources/prs/flashinfer/PR-2443.md |
| MTP for mamba |
sources/prs/flashinfer/PR-2444.md |
| feat: Add MXFP8 GEMM mm_mxfp8 (cutlass) |
sources/prs/flashinfer/PR-2464.md |
| refactor: Port upstream CUTLASS fixes and refactor grouped_gemm_nt_masked GEMM module location |
sources/prs/flashinfer/PR-2503.md |
| feat: cute dsl mmfp4 for blackwell |
sources/prs/flashinfer/PR-2540.md |
Implement cutlass_fused_moe mxfp8 |
sources/prs/flashinfer/PR-2581.md |
| feat: trtllm tinygemm2 in flashinfer as bf16 routergemm |
sources/prs/flashinfer/PR-2587.md |
| Mamba SSU: better automatic kernel selection + algorithm selection optionally exposed to the user. |
sources/prs/flashinfer/PR-2591.md |
| int16 Block-Scaled State and Stochastic Rounding for SSU (mamba) |
sources/prs/flashinfer/PR-2645.md |
| feat: support mxfp4 & mxfp8 entrypoint for blackwell cutedsl dense gemm |
sources/prs/flashinfer/PR-2660.md |
| Add NVFP4 KV cache quantization support for SM100 |
sources/prs/flashinfer/PR-2702.md |
| Mamba2 SSD Combined Forward Pass (Blackwell CuTe DSL Kernel) |
sources/prs/flashinfer/PR-2709.md |
| feat: Add DiT-oriented kernels where Qk (Bmm1) type can be reinterpreted into Int8 or BFloat16 |
sources/prs/flashinfer/PR-2711.md |
| [gdn] support non-contiguous state for decoding |
sources/prs/flashinfer/PR-2727.md |
| Add cute dsl mla decode op |
sources/prs/flashinfer/PR-2743.md |
| feat: Add FP4 KV cache quant/dequant kernels |
sources/prs/flashinfer/PR-2757.md |
| perf: Performance tune cute dsl RMSNorm variants |
sources/prs/flashinfer/PR-2777.md |
| feat: FP8 output support for CUTLASS MLA paged attention |
sources/prs/flashinfer/PR-2779.md |
| [CuTe DSL] Add modular FMHA prefill and MLA decode attention kernels |
sources/prs/flashinfer/PR-2805.md |
| [Fmha] Sparse MLA decode kernel selection heuristics |
sources/prs/flashinfer/PR-2836.md |
| feat: Add CuTe-DSL backend for NVFP4 quantization |
sources/prs/flashinfer/PR-2838.md |
| Mamba SSU: horizontal MTP kernel (+ DSTATE=96 support) |
sources/prs/flashinfer/PR-2865.md |
| perf: Optimize CuTe-DSL fp4 and fp8 quantization kernels |
sources/prs/flashinfer/PR-2904.md |
| [NVIDIA] fix(jit): enable GDC for CUTLASS fused MoE PDL — prevent random crashes on SM12x |
sources/prs/flashinfer/PR-2913.md |
feat: Add cuBLASLt backend for mm_bf16 and enable multi-tactic autotuning for FP8/MXFP8 runners |
sources/prs/flashinfer/PR-2914.md |
| feat: Add CuTe DSL grouped-gemm + combine fusion support |
sources/prs/flashinfer/PR-2944.md |
| fix: use float instead of double in sampling binary search to avoid FP64 bottleneck on SM103 |
sources/prs/flashinfer/PR-2945.md |
Improved simple mamba SSU kernel |
sources/prs/flashinfer/PR-2962.md |
| Add flashinfer.fused_rmsnorm_silu() with native kernel backend |
sources/prs/flashinfer/PR-2965.md |
| [feat] Add blackwell GDN prefill kernel |
sources/prs/flashinfer/PR-3001.md |
| [feat] Add routing_replay_out support to MoE kernels and Python API |
sources/prs/flashinfer/PR-3024.md |
| perf: Port TRT-LLM SM120/SM121 FP4 CUTLASS GEMM optimizations. Add PDL |
sources/prs/flashinfer/PR-3026.md |
| [feat] Trtllm-gen Per-token Nvfp4 MoE |
sources/prs/flashinfer/PR-3027.md |
| feat: Add b12x CuTe DSL fused MoE for SM120 |
sources/prs/flashinfer/PR-3066.md |
| feat: DiT layer norm fusions for WAN: flashinfer.diffusion_ops |
sources/prs/flashinfer/PR-3157.md |
| fix(cute_dsl/moe): make autotuner bucket configuration adapt to runtime input |
sources/prs/flashinfer/PR-3216.md |
| Support Kimi K2.5 H64 CuTe DSL MLA decode |
sources/prs/flashinfer/PR-3235.md |
| Ameyn/gdn bf16 dispatcher and 4d pool |
sources/prs/flashinfer/PR-3268.md |
| feat(cute_dsl/moe): deterministic balanced autotune profile inputs |
sources/prs/flashinfer/PR-3286.md |
| checkpointing_ssu kernel: fused replay + conditional state-write for Mamba2 |
sources/prs/flashinfer/PR-3324.md |
[CUDA][avgpool2d] Fix backward launch bounds again for sm100, sm120 |
sources/prs/pytorch/PR-150640.md |
[CUDA][avgpool2d] Fix backward launch bounds again for sm100, sm120 |
sources/prs/pytorch/PR-150676.md |
| feat: Add FP4 (E2M1) KV Cache Support with Quantization Utilities for MLA |
sources/prs/sglang/PR-10078.md |
| [NVIDIA] Add new SMs support for Spark & Thor |
sources/prs/sglang/PR-11287.md |
| [sgl-kernel][1/N]Support Expert Specialization Grouped GEMM |
sources/prs/sglang/PR-11432.md |
| [DeepseekV32] Enable flashmla_prefill kernel with fp8 kvcache |
sources/prs/sglang/PR-11655.md |
| support cutlass fp4 kernel in sm120 |
sources/prs/sglang/PR-11737.md |
| [sgl-kernel][Feat][B200][1/N]Support MXFP8 Grouped GEMM in Blackwell |
sources/prs/sglang/PR-13731.md |
| [sgl-kernel][Feat][B200][2/N] Support MXFP8 Grouped GEMM in Blackwell |
sources/prs/sglang/PR-14640.md |
| [NVIDIA] upstream FA4 |
sources/prs/sglang/PR-15182.md |
| [jit-kernel] Add CuTe DSL GDN Decode Kernel |
sources/prs/sglang/PR-15631.md |
| Move fa4 from sgl-kernel to jit kernel |
sources/prs/sglang/PR-17353.md |
| Add mxfp8 support for online quantization, Triton dense linear, and CUTLASS MoE |
sources/prs/sglang/PR-17449.md |
| [Diffsuion & JIT_kernel] QKNorm cross heads kernel |
sources/prs/sglang/PR-18073.md |
| feat: add FA4 SM90 paged KV decode support & update attention docs |
sources/prs/sglang/PR-18442.md |
| [FIX] Correct JIT kernel compilation on newer GPUs with outdated driver metadata. |
sources/prs/sglang/PR-18496.md |
| [Kernel Slimming] Migrate NVFP4 kernels to JIT |
sources/prs/sglang/PR-19437.md |
| [Feature] NVFP4 Marlin fallback for non-Blackwell GPUs (SM75+) |
sources/prs/sglang/PR-19652.md |
| [JIT Kernel] Reland NVFP4 kernels to JIT |
sources/prs/sglang/PR-20012.md |
| Fix(jit): support rmsnorm for hidden_size in {64, 128, 256} |
sources/prs/sglang/PR-20661.md |
| CUTLASS NVFP4 GEMM improvement of SM120 |
sources/prs/sglang/PR-21314.md |
| Fused_qknorm_rope kernel optimization: up to 2.4× faster |
sources/prs/sglang/PR-21654.md |
| [Diffusion] Fix weight scale swizzle and add large-M kernel config for FLUX.2-dev-NVFP4 |
sources/prs/sglang/PR-22064.md |
| [nvidia] Gemma4 nvfp4 fix |
sources/prs/sglang/PR-22079.md |
| [Refactor] Rename NSA → DSA: user-facing aliases, file/class/import rename |
sources/prs/sglang/PR-25821.md |
| Support FP4 gemm (1/2) |
sources/prs/sglang/PR-3899.md |
| Support Blackwell Block Scale FP8 Gemm |
sources/prs/sglang/PR-4278.md |
| support cmake for sgl-kernel |
sources/prs/sglang/PR-4706.md |
| [Build] Fix cuda12.8 build error in nvfp4_scaled_mm_kernels.cu |
sources/prs/sglang/PR-4953.md |
| [1/2] Add FP8 Blockscale MoE CUTLASS kernel for Blackwell |
sources/prs/sglang/PR-5281.md |
| [2/2] Add python wrapper for CUTLASS FP8 Blockscale MoE Kernel. |
sources/prs/sglang/PR-5694.md |
| [1/2] Add Kernel support for Cutlass based Fused FP4 MoE |
sources/prs/sglang/PR-6093.md |
| Add a CUDA kernel for fusing mapping and weighted sum for MoE. |
sources/prs/sglang/PR-6916.md |
| [perf][sgl-kernel] extend cutlass_mla_decode to support num_head < 128 |
sources/prs/sglang/PR-6929.md |
| chore: upgrade flashinfer v0.2.6.post1 jit |
sources/prs/sglang/PR-6958.md |
| Add CUTLASS FP8 Blockscale MoE kernel for Hopper architecture |
sources/prs/sglang/PR-7278.md |
| [Perf] Tunings for SM100 FP8 CUTLASS kernel |
sources/prs/sglang/PR-8818.md |
| optimize: reduce shulffle and quantization overhead in cutlass_moe sm90 |
sources/prs/sglang/PR-8962.md |
[NVIDIA] [2/N] Optimize silu_and_mul_scaled_fp4_grouped_quant perf |
sources/prs/sglang/PR-9556.md |
| Make sm100 fp8 kernels available on sm103 |
sources/prs/sglang/PR-9789.md |
| Make fp4_quantize kernels work on sm103 |
sources/prs/sglang/PR-9807.md |
| [Model] Support Meituan LongCat-Flash && LongCat-Flash-MTP |
sources/prs/sglang/PR-9824.md |
| [WIP] support more dtypes for tcgen05 |
sources/prs/tilelang/PR-1229.md |
| [Enhancement] add more dtype and fix mma.ws for fp16 for tcgen05 |
sources/prs/tilelang/PR-1327.md |
| [CUDA] Support tcgen5mma gemm ts |
sources/prs/tilelang/PR-1866.md |
| [Feature] Support cluster launch, query, synchronization and barrier operations |
sources/prs/tilelang/PR-1874.md |
| [Feature] 2-SM support for TMA, TMEM and TCGEN5MMA on Blackwell |
sources/prs/tilelang/PR-1882.md |
| [Feature] Block-scaled GEMM support for MXFP8 on Blackwell |
sources/prs/tilelang/PR-1945.md |
| [Transform] Add InjectTcgen05Fence pass |
sources/prs/tilelang/PR-2003.md |
| [codex] Split GEMM implementations by backend |
sources/prs/tilelang/PR-2153.md |
| [NVIDIA] Support nvfp4 cutlass gemm |
sources/prs/vllm/PR-13571.md |
| add cutlass support for blackwell fp8 gemm |
sources/prs/vllm/PR-13798.md |
| Add cutlass support for blackwell fp8 blockwise gemm |
sources/prs/vllm/PR-14383.md |
| [NVIDIA] Support Cutlass w8a8 FP8 for Blackwell Geforce GPUs (sm120) |
sources/prs/vllm/PR-17280.md |
| Sm100 blockwise fp8 swap ab |
sources/prs/vllm/PR-18564.md |
| [Perf] Tunings for SM100 FP8 CUTLASS kernel |
sources/prs/vllm/PR-18778.md |
| [Hardware][NVIDIA] FP4 MoE kernel optimization |
sources/prs/vllm/PR-19110.md |
| [Hardware][NVIDIA][kernel] Fp4 MOE quant kernel optimization |
sources/prs/vllm/PR-19500.md |
| [Perf] Further tunings for SM100 FP8 CUTLASS kernel |
sources/prs/vllm/PR-19566.md |
| [feat]: CUTLASS block scaled group gemm for SM100 |
sources/prs/vllm/PR-19757.md |
| [Feature] Integrate SM100 DeepGEMM support |
sources/prs/vllm/PR-20087.md |
| [Kernel] SM90 CUTLASS FP8 GEMM: add support for swap AB + kernel tuning |
sources/prs/vllm/PR-20396.md |
| [feat]: add SM100 support for cutlass FP8 groupGEMM |
sources/prs/vllm/PR-20447.md |
| SM100 Cutlass MLA decode with unrestricted num_heads (< 128) for DeepSeek TP |
sources/prs/vllm/PR-20769.md |
| [fix]: disable cutlass block scaled group gemm for EP |
sources/prs/vllm/PR-20781.md |
| [Perf] Cuda Kernel for Per Token Group Quant |
sources/prs/vllm/PR-21083.md |
| [Bug] Fix B200 DeepGEMM E8M0 Accuracy Issue |
sources/prs/vllm/PR-22399.md |
| [Perf] Use upstream CUTLASS for SM90 Block FP8 kernel |
sources/prs/vllm/PR-23280.md |
| [Compile] Fix Compile Warning SM100 Cutlass MLA |
sources/prs/vllm/PR-23287.md |
| [NVIDIA] Support SiluMul + NVFP4 quant fusion |
sources/prs/vllm/PR-23671.md |
| [Kernel] Support decode context parallelism on Blackwell with CUTLASS MLA |
sources/prs/vllm/PR-24385.md |
| [Transform] [Quantization] Add QuTLASS support to vLLM |
sources/prs/vllm/PR-24440.md |
| [NVIDIA] Blackwell Family |
sources/prs/vllm/PR-24673.md |
| [Kernel][Quantization] add w4a8 support for marlin kernel |
sources/prs/vllm/PR-24722.md |
| [Perf] SM100 - add swap AB optimization to CUTLASS FP8 GEMM |
sources/prs/vllm/PR-27284.md |
| [Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM |
sources/prs/vllm/PR-28124.md |
| [Performance][B200] silu_mul_quant: pack scales in int32 |
sources/prs/vllm/PR-28358.md |
| [Kernel] Add NVFP4 MoE CUTLASS support for SM120 |
sources/prs/vllm/PR-29242.md |
| [Perf][Kernel] Optimize FP4 quantization kernels (SM100F) |
sources/prs/vllm/PR-32520.md |
| [Performance] Tune Mamba selective scan kernel for B200 |
sources/prs/vllm/PR-32873.md |
| [Spec Decode] Unified Parallel Drafting |
sources/prs/vllm/PR-32887.md |
| [Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels |
sources/prs/vllm/PR-34448.md |
| [Quantization] add humming quantization kernel |
sources/prs/vllm/PR-34556.md |
| [Bugfix] Gate 256-bit instructions to CUDA 12.9+ |
sources/prs/vllm/PR-34791.md |
| [BUGFIX][Mamba][Qwen3.5] Zero freed SSM cache blocks on GPU |
sources/prs/vllm/PR-35219.md |
| [Mamba] Add stochastic rounding support |
sources/prs/vllm/PR-35753.md |
| [Kernel] Fuse FP8 output quantization into merge_attn_states |
sources/prs/vllm/PR-36518.md |
| [Feat][Spec Decode] DFlash |
sources/prs/vllm/PR-36847.md |
| [Kernel] Add non-gated support for NVFP4 CUTLASS MoE |
sources/prs/vllm/PR-37320.md |
| Add nvfp4 support to reshape_and_cache_flash |
sources/prs/vllm/PR-37332.md |
| [Perf][Kernel] Persistent TopK scheduler: unified CUDAGraph-safe kernel with dynamic per-row dispatch - DeepSeek-V3.2 DSA decode |
sources/prs/vllm/PR-37421.md |
| [Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 |
sources/prs/vllm/PR-37463.md |
| [4/n] Migrate FP4/W4A8 CUTLASS kernels to torch stable ABI |
sources/prs/vllm/PR-37503.md |
| [Perf] triton bilinear_pos_embed kernel for ViT |
sources/prs/vllm/PR-37948.md |
| [Perf] FP8 FlashInfer Attn for ViT |
sources/prs/vllm/PR-38065.md |
| [NVIDIA] Bugfix NVFP4 DGX Spark and RTX50 |
sources/prs/vllm/PR-38423.md |
| [Refactor] Improve indexer decode path metadata preparation |
sources/prs/vllm/PR-38865.md |
| [Perf][GDN] Align TMA usage with upstream FLA |
sources/prs/vllm/PR-38981.md |
| [Bugfix] Guard mxfp4_experts_quant bindings on ENABLE_NVFP4_SM100 |
sources/prs/vllm/PR-40191.md |
| [Perf] Batch invariance with Cutlass fp8 support, 28.9% E2E latency improvement |
sources/prs/vllm/PR-40408.md |
| [DSv4] Improved fused Indexer Q quant kernel |
sources/prs/vllm/PR-41428.md |
| [DSv4] Improved dequant gather K cache kernel |
sources/prs/vllm/PR-42236.md |
| Two-CTA Cooperative MMA |
wiki/hardware/2sm-cooperative.md |
| Cluster Launch Control (CLC) |
wiki/hardware/clc.md |
| mbarrier (Memory Barrier Primitives) |
wiki/hardware/mbarrier.md |
| NVFP4 and block-scaled narrow precision |
wiki/hardware/nvfp4.md |
| Programmatic Dependent Launch / Grid Dependency Control |
wiki/hardware/pdl-gdc.md |
| tcgen05.mma — Fifth-Generation Tensor Core MMA |
wiki/hardware/tcgen05-mma.md |
| Tensor Memory Accelerator (TMA) |
wiki/hardware/tma.md |
| Tensor Memory (TMEM) |
wiki/hardware/tmem.md |
| DeepGEMM — runtime-JIT tensor-core kernels |
wiki/kernels/deepgemm.md |
| FlashAttention-4 |
wiki/kernels/flash-attention-4.md |
| FlashAttention SM100 MLA TopK Sparse Forward |
wiki/kernels/flash-attention-sm100-mla-topk.md |
| FlashMLA attention kernels |
wiki/kernels/flashmla.md |
| FP8 block-scale GEMM |
wiki/kernels/fp8-block-scale-gemm.md |
| Fused MoE — Expert GEMM and Adjacent Operations |
wiki/kernels/fused-moe.md |
| Gated Delta Network kernels |
wiki/kernels/gated-delta-net.md |
| Gated Dual GEMM (Gate-Up + Activation) |
wiki/kernels/gated-dual-gemm.md |
| Grouped GEMM for MoE |
wiki/kernels/grouped-gemm.md |
| NVFP4 GEMM |
wiki/kernels/nvfp4-gemm.md |
| NVFP4 batched GEMV |
wiki/kernels/nvfp4-gemv.md |
| Sparse MLA |
wiki/kernels/sparse-mla.md |
| TensorRT-LLM Blackwell FP4 DSA Indexer |
wiki/kernels/tensorrt-llm-blackwell-indexer.md |
| CUDA C++ for Blackwell Kernels |
wiki/languages/cuda-cpp.md |
| CuTe DSL for Blackwell |
wiki/languages/cute-dsl.md |
| PTX for SM100 |
wiki/languages/ptx-sm100.md |
| Triton on Blackwell |
wiki/languages/triton-blackwell.md |
| PTX Cache Policy Differentiation |
wiki/techniques/cache-policy.md |
| CCCL CUB SM100 Scan Tuning |
wiki/techniques/cccl-memory-primitives.md |
| Double/Multi-Buffering Patterns |
wiki/techniques/double-buffering.md |
| Epilogue fusion |
wiki/techniques/epilogue-fusion.md |
| External Source-Map Research For Kernel Edits |
wiki/techniques/external-source-map-research.md |
| Fine-grained FP8/FP4 scaling |
wiki/techniques/fine-grained-quantization.md |
| Kernel fusion |
wiki/techniques/kernel-fusion.md |
| Persistent Kernels with Cluster Launch Control |
wiki/techniques/persistent-kernels.md |
| Ping-Pong Scheduling |
wiki/techniques/ping-pong-scheduling.md |
| Software Pipelining and Multi-Stage Buffering |
wiki/techniques/pipeline-stages.md |
| Register budgeting |
wiki/techniques/register-budgeting.md |
| Software-Emulated Exponential |
wiki/techniques/software-exp.md |
| Shared Memory Swizzling |
wiki/techniques/swizzling.md |
| Tile Scheduling Strategies |
wiki/techniques/tile-scheduling.md |
| Wide Vectorized Loads and Cache Policies |
wiki/techniques/vectorized-loads.md |
| Warp Specialization on Hopper and Blackwell |
wiki/techniques/warp-specialization.md |