Osama Jaber

Jaber Jaber, Osama Jaber

Open Arabic large language models split into two classes: sub-1B multilingual models that treat Arabic as an afterthought (Qwen2.5-0.5B, Falcon-H1-0.5B), and 7B-70B Arabic-specialized models that require a server to run (Jais, AceGPT, ALLaM, SILMA). The one published attempt at a sub-2B Arabic-specialized model, Kuwain-1.5B, never released its weights. We present RightNow-Arabic-0.5B-Turbo, a 518M-parameter Arabic-specialized decoder LLM built on Qwen2.5-0.5B. The pipeline adds 27,032 Arabic tokens via mean-subtoken initialization, continues pretraining on 504M Arabic tokens on 8xH100 with FSDP, FlashAttention varlen packing, and Liger fused kernels, then applies supervised fine-tuning on 129,116 Arabic instruction pairs with response-only loss masking, direct preference optimization on 6,750 Arabic preference pairs, and weight soup merging across three checkpoints. On three lm-evaluation-harness Arabic benchmarks (COPA-ar, Arabic HellaSwag, ArabicMMLU) the merged model reaches 35.9% mean accuracy, beats every same-class open model, ties Falcon-H1-1.5B on COPA-ar (58.4%) at one-third the size, and recovers 67% of SILMA-9B's mean at 1/18 the parameters. The edge build quantizes to 398 MB (q4_k_m) and delivers 635 tokens/s at batch size 1 on a single H100 via llama.cpp. All code (5,555 lines across 25 scripts), weights (bf16, int8, and four GGUF quantizations), and benchmark scripts are released at https://huggingface.co/RightNowAI/RightNow-Arabic-0.5B-Turbo.

Jaber Jaber, Osama Jaber

Writing high-performance GPU kernels is among the most labor-intensive tasks in machine learning systems engineering. We present AutoKernel, an open-source framework that applies an autonomous agent loop to GPU kernel optimization for arbitrary PyTorch models. Given a model, AutoKernel profiles it to identify computational bottlenecks, ranks them by Amdahl's law impact, and iteratively refines Triton or CUDA C++ kernel implementations through hundreds of experiments without human intervention. A five-stage correctness harness covering smoke tests, shape sweeps, numerical stability, determinism verification, and edge-case coverage ensures every candidate kernel is validated before any speedup is recorded. The system comprises over 9,000 lines of Python, 18 starter kernel implementations across two backends, a six-tier optimization playbook, and integration with the KernelBench benchmark suite. AutoKernel covers nine kernel types spanning the dominant operations in modern transformer architectures. On an NVIDIA H100, our Triton kernels outperform both PyTorch eager and torch.compile (max-autotune) on the majority of tested configurations: 5.29x over eager on RMSNorm, 2.82x on softmax, and 2.21x on cross-entropy, while beating torch.compile by 2.83x, 3.44x, and 2.94x respectively. In community deployment, an AutoKernel-optimized kernel achieved first place on the vectorsum_v2 B200 leaderboard. The full system is available at https://github.com/RightNow-AI/autokernel.

Jaber Jaber, Osama Jaber

World models that predict future states from video remain limited by flat latent representations that entangle objects, ignore causal structure, and collapse temporal dynamics into a single scale. We present HCLSM, a world model architecture that operates on three interconnected principles: object-centric decomposition via slot attention with spatial broadcast decoding, hierarchical temporal dynamics through a three-level engine combining selective state space models for continuous physics, sparse transformers for discrete events, and compressed transformers for abstract goals, and causal structure learning through graph neural network interaction patterns. HCLSM introduces a two-stage training protocol where spatial reconstruction forces slot specialization before dynamics prediction begins. We train a 68M-parameter model on the PushT robotic manipulation benchmark from the Open X-Embodiment dataset, achieving 0.008 MSE next-state prediction loss with emerging spatial decomposition (SBD loss: 0.0075) and learned event boundaries. A custom Triton kernel for the SSM scan delivers 38x speedup over sequential PyTorch. The full system spans 8,478 lines of Python across 51 modules with 171 unit tests. Code: https://github.com/rightnow-ai/hclsm

Jaber Jaber, Osama Jaber

DeepSeek-V3.2 and V4 introduce Compressed Sparse Attention (CSA): a lightning indexer (a learned scoring projection over compressed keys) scores them, the top-k are selected per query, and a sparse attention kernel reads only those. Public CSA implementations materialize a [B, S, H_I, T] FP32 score tensor before the top-k reduction. With H_I=64 indexer heads and the V4-Flash compression ratio m=4, that intermediate is 256 GB at sequence length S=65,536, exceeding any single-GPU high-bandwidth-memory (HBM) budget. We present StreamIndex, a Triton implementation of the CSA pipeline whose central component is a chunked partition-merge top-k driver that never materializes the full intermediate. On synthetic-but-realistic V4-shaped inputs at the indexer-step (layer) level on a single NVIDIA H200, the materialize path runs out of memory (OOMs) at S=65,536 with V4-Flash dimensions; StreamIndex runs the same indexer to S=1,048,576 with 6.21 GB peak HBM, a 32x regime extension. Set-overlap recall against the materialize ground truth is bit-exact at small S where both fit; across three 5-point design-space sweeps (chunk size, key-tile size, top-k), mean recall rounds to 1.0000 with min recall at least 0.9980 in every cell. The chunked driver composes with TileLang's pipelined attention kernel: at S=262,144 with V4-Flash dimensions, the materialize indexer paired with TileLang attention OOMs while the chunked indexer paired with the same attention runs in 1.97 s at 18.56 GB peak. Our contribution targets the indexer step; we make no claim of a faster attention kernel or of real-checkpoint end-to-end behavior. Code: https://github.com/RightNow-AI/StreamIndex.

Jaber Jaber, Osama Jaber

Large language models run every token through every layer, regardless of difficulty. We present TIDE, a post-training system that attaches tiny learned routers at periodic checkpoint layers and, at inference time, selects the earliest layer whose hidden state has converged for each token. TIDE requires no model retraining, works with any HuggingFace causal LM, auto-detects GPU architecture, and supports float32, float16, and bfloat16 through fused CUDA kernels. On an NVIDIA A100 with DeepSeek R1 Distill 8B, TIDE achieves 100% prefill exit rate (5% of tokens exit at layer 11, the remaining at layer 31), reduces prefill latency by 7.2%, and increases single-batch throughput by 6.6%. During autoregressive decoding, 98-99% of tokens exit early while the model correctly solves a multi-step math problem with 95 unique output tokens. On Qwen3 8B (36 layers), throughput improves by 8.1% at batch size 8. Calibration on 2,000 WikiText samples takes under 3 minutes and produces a ~4 MB router checkpoint. The system comprises 1,308 lines of Python and 1,081 lines of CUDA/C++ with 74 passing tests. Code: https://github.com/RightNow-AI/TIDE

Jaber Jaber, Osama Jaber

Recursive transformers reuse a shared weight block across multiple depth steps, trading parameters for compute. A core limitation: every step applies the same transformation, preventing the model from composing distinct operations across depth. We present Ouroboros, a system that attaches a compact Controller hypernetwork to a recursive transformer block. The Controller observes the current hidden state, produces a per-step diagonal modulation vector, and applies it to frozen SVD-initialized LoRA bases, making each recurrence step input-dependent. We combine this with gated recurrence (bias-initialized to 88% retention) and per-step LayerNorm for stable deep iteration. On Qwen2.5-3B split into a Prelude/Recurrent/Coda architecture (17 of 36 layers retained), Ouroboros reduces training loss by 43.4% over the unmodified 17-layer baseline, recovering 51.3% of the performance gap caused by layer removal. The full system adds only 9.2M trainable parameters (Controller, gate, and per-step norms) yet outperforms equivalently-sized static per-step LoRA by 1.44 loss points at depth 1 and remains ahead across all tested depths (1, 4, 8, 16) and ranks (8, 32, 64). We also find that gated recurrence is essential: without it, recursive layer application makes the model strictly worse. These gains are measured on the training distribution; on held-out text, the Controller does not yet improve over the baseline, a limitation we attribute to frozen downstream layers and discuss in detail. Code: https://github.com/RightNow-AI/ouroboros