Tootfinder

Over asielopvang en burgemeesters.
https://www.nrc.nl/nieuws/2026/05/22/terwijl-den-haag-verwarring-zaait-probere…

@… Zawsze mam to samo, plus dziwne akcje z żulami, spóźnienia - na tyle, że jak muszę już pociągiem jechać na samolot czy na daną godzinę, to biorę taki minimum 4 godziny wcześniej (czasem dzień wcześniej, jak drogi bilet), żeby na pewno zdążyć. 50/50 czy to będzie normalny pociąg, czy upakowany gorzej niż ryanair, jakieś krzywe akcje z…

On the fundamental solutions of two nonlocal parabolic equations related to logarithmic Laplacians
Bart Rosenzweig, Jonathan Stanfill
https://arxiv.org/abs/2606.04225 https://arxiv.org/pdf/2606.04225 https://arxiv.org/html/2606.04225
arXiv:2606.04225v1 Announce Type: new
Abstract: We answer in the affirmative a question posed by V. Maz'ya of whether one can continue as a meromorphic function of $t$ the series representation of the fundamental solution of a certain nonlocal parabolic equation associated to a logarithmic Laplacian on the circle, which arises in the study of boundary value problems associated to the ordinary Laplacian on domains with thin cavities. The $a\ln(n) O(1)$ growth of the eigenvalues of the integral operator, together with explicit formulas for the eigenfunctions and the subleading asymptotic behavior of the eigenvalues, allows us to show that the fundamental solution is reminiscent of a sum of shifted Riemann zeta functions or polylogarithms, depending on the spatial variable. We show an analogous result for an operator related to a different logarithmic Laplacian on the interval, whose structure is similar. Along the way we are led to prove and to conjecture a number of curious identities involving Bell polynomials and Bernoulli numbers related to the exponential of the digamma function which are of independent interest.
toXiv_bot_toot

RTP-LLM: High-Performance Alibaba LLM Inference Engine
Boyu Tan, Jiarui Guo, Zongwei Lv, Hanbo Sun, Tong Yang, Kan Liu, Xinfei Shi, Zetao Hu, Yaxin Yu, Chi Zhang, Jianning Zhang, Xi Yang, Wei Zhang, Bo Cai, Silu Zhou, Xiyu Wang, Na He, Yinghao Yu, Wending Bao, Guiyang Huang, Yuxing Yuan, Juncheng Yin, Nan Wang, Lin Yang, Zechao Zhang, Lu Chen, Guoding Li, Tao Lan, Lin Qu
https://arxiv.org/abs/2605.29639 https://arxiv.org/pdf/2605.29639 https://arxiv.org/html/2605.29639
arXiv:2605.29639v1 Announce Type: new
Abstract: Large Language Models (LLMs) have revolutionized AI applications, but deploying them at scale presents significant challenges. We present RTP-LLM, a high-performance inference engine for industrial-scale LLM deployment, successfully deployed across Alibaba Group serving over 100 million users. RTP-LLM addresses fundamental bottlenecks through integrated design. It optimizes model loading via file-order-driven I/O and parallel I/O-communication overlapping. The Prefill-Decode Disaggregation architecture decouples compute-intensive prefill from memory-bound decode phases, combined with hierarchical multi-tiered KV cache management enabling efficient cache reuse. In addition, RTP-LLM incorporates modular speculative decoding supporting multiple algorithms, adaptive KV cache quantization, and decoupled multimodal processing, with support for multi-level parallelism.
Comprehensive evaluations across diverse model architectures (8B-235B parameters) have been conducted, where both controlled benchmarks and real production workloads are used. The results demonstrate RTP-LLM's superior performance against vLLM and SGLang: 4.7x-6.3x model loading speedup, 35-37% TTFT P95 latency reduction with 215% cache reuse improvement in production traffic scheduling, 1.12x-2.48x and 1.86x-2.52x throughput improvements in speculative decoding and multimodal inference, respectively, and 35-40% batch latency reduction with 1.9x-3.0x TTFT improvement in quantized inference. RTP-LLM's production-proven architecture and open-source availability make it a comprehensive solution for industrial LLM deployment.
toXiv_bot_toot

Testowałem sobie ostatnio https://github.com/code-yeongyu/oh-my-openagent - i to kolejny slop projekt...

Pomijając przepalanie tokenów jak szalony (w końcu został w taki sposób zaprojektowany) to po prostu nie działa.

Orchestracja agentów się zawiesza, opencode nie dostaje potem statusu z zakończonych zadań i przestaje pracować, cały flow niepoprawnie liczy tokeny na głównej sesji i kończy mając w zapasie ciąg…

🇺🇦 #NowPlaying on BBCRadio3's #Breakfast
Max Bruch, Randall Goosby, The Philadelphia Orchestra & Yannick Nézet‐Séguin:
🎵 Violin Concerto No 1 in G minor, Op 26 (2nd mvt)
#MaxBruch #RandallGoosby #ThePhiladelphiaOrchestra #YannickNézetSéguin
Please 🔁 BOOST to share what you like
- your followers don't see if you ⭐ favourite a post