Knowledge catalogue
arXiv:2605.25475v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows line
arXiv:2605.25092v1 Announce Type: cross Abstract: Long-term conversational memory is a retrieval workload classical IR was not built for: the index grows during the query stream, query types shift int
LlamaIndex is recruiting and inviting interested candidates to explore career opportunities with the company. This post, shared by Jerry Liu (LlamaIndex's founder), encourages potential applicants to
model: add Qwen3.8-Flash-Next (qwen4exp) (#27742) gguf: add qwen4exp (Qwen3.8-Flash-Next) arch and converter Adds the GGUF-side plumbing for HF model_type qwen4_exp: MODEL_ARCH.QWEN4EXP plus tensors f
Feature: Added LIGHTNING_INDEXER support for Deepseek V4 ops on Vulkan Backend (#27453) vulkan: add LIGHTNING_INDEXER op vulkan: updated lightning_indexer.comp and ggml-vulkan.cpp with 128-lane dot-pr
AlloyDB powers enterprise-grade search for some of the largest organizations, providing robust hybrid search capabilities that combine text, vector, and keyword searches into a simple ranked SQL query
For modern AI and RAG applications, achieving high search relevance requires that you combine at least two techniques: vector search for semantic context, and full-text search (FTS) for keyword precis
Automated lint: 51 errors, 15 warnings, 3 info
Automated lint: 49 errors, 14 warnings, 3 info
Automated lint: 48 errors, 13 warnings, 3 info
Automated lint: 47 errors, 12 warnings, 3 info
Automated lint: 45 errors, 11 warnings, 3 info
Automated lint: 44 errors, 10 warnings, 3 info
Automated lint: 43 errors, 9 warnings, 3 info
Automated lint: 34 errors, 0 warnings, 3 info
qwen4exp : halve the indexer score memory (#29825) qwen4exp : halve the indexer score memory The indexer scored all heads in one product and rectified a copy of it, so two [n_pool, n_idx_h, n_tokens]
AlloyDB is a fully managed, PostgreSQL-compatible database service built for your most demanding enterprise workloads. It combines the best of open source PostgreSQL with Google’s advanced technology,
Vector search is a critical component of generative AI, retrieval-augmented generation (RAG), and data agent architectures, but sometimes vector search alone isn't enough. While vector embeddings are
Auto-generated index of all companies mentioned across the wiki.
Auto-generated index of all models mentioned across the wiki.
Auto-generated index of all people mentioned across the wiki.
Auto-generated index of all tools mentioned across the wiki.
Auto-generated index of all papers mentioned across the wiki.
tests : run test-save-load-state across all architectures (#27755) tests : run test-save-load-state across all architectures test-save-load-state previously only ran in ctest against a single download
metal: implement DSv4 Lightning Indexer (#25893) metal: implement F16 Lightning Indexer Implement GGML_OP_LIGHTNING_INDEXER for 128-dimensional, 64-head inputs with F32 queries and weights plus F16 ke
I've been out of these forums for awhile but I figured I would provide a formal update on how this has been going now that it has some operation time under its belt, just to put the information out th
llama : allocate indexer cache only in 'full' indexer layers (#26474) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Appl
arXiv:2607.23772v1 Announce Type: cross Abstract: We study a restless multi-armed bandit (RMAB) problem for a stochastic deadline scheduling application. RMAB problems are solved using the Whittle ind
Alibaba has released Qwen Audio 3.0 Realtime, with the Plus variant debuting as the new #1 model on the Artificial Analysis Speech to Speech Index at 84.1%, ahead of GPT-Realtime-2.1 High at 79.1% Rel
cuda: tile the lightning indexer over keys and tokens for 4 heads (#29901) cuda: tile the lightning indexer over keys and tokens for 4 heads With too few heads for a wmma tile, a block scores 64 keys
Overview llama.cpp v0.6.0 introduces the new llama_batch_ext extended batch API (with llama_process) for mixed token/embedding inputs and MTP/deepstack state embeddings, adds support for the GLM-5.3-F
arXiv:2609.02143v1 Announce Type: cross Abstract: Most vector databases rely on graph-based indexes, notably HNSW and Vamana, for approximate nearest neighbor search. With embedding models widely adop
arXiv:2609.01633v1 Announce Type: cross Abstract: A composite structural index summarises a network in one number; for a triangle-based index it is spectrally redundant: Tr(A^3) is the third moment of
metal : add sparse FA (#28098) metal : support n_kv_max sparse mask hint in flash attention vec kernel add kernel_flash_attn_ext_vec_idx: compacts finite mask entries into a per-row index list (Hillis
sycl: contiguous fast path + 32-bit index math for unary elementwise ops (#25946) sycl: contiguous fast path + 32-bit index math for unary elementwise ops sycl: use fastdiv for elementwise index math
Inspired by DigUp for macOS, VectorDash aims to be a full Windows 11 search replacement, powered by EmbeddingGemma 2. Full indexing: search by meaning or exact words across photos, screenshots, audio,
Editor's note: Lucius AI, a tender-intelligence startup covering markets across five continents, runs its entire data platform on AlloyDB for PostgreSQL with a single operator. By migrating semantic s
I'm pretty sure it can be done with any model based on qwen4exp, which Qwen's next local models will be based on. You can use a quant that barely fits in VRAM and still run at the model's maximum cont
arXiv:2609.17012v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one
The intelligence in my context is an aggregate index, I called the Agentic Coding Index, across most relevant agentic coding benchmarks: SWE-bench Pro, DeepSWE v1.1, Terminal-Bench (v4, v3, v2.1), Cod
arXiv:2608.24079v1 Announce Type: cross Abstract: A shared search-and-recommendation index must score new items from features alone because search has no exploration slot. In a public log covering bot
mtmd: Add Vision Support for Minimax-M3 (#25113) Add preliminary MiniMax-M3 support Text-only port that re-uses existing components: MiniMax-M2 style GQA with per-head QK-norm and partial rotary, Deep
arXiv:2606.27061v1 Announce Type: new Abstract: External indexes can be used for cluster evaluation when ground truth is available. We review the most common external validity indexes focusing on set-
Enterprise AI agents need persistent memory to execute complex, multi-day workflows and long-horizon tasks. In this blog, we examine how a 2-tier memory architecture using Memorystore for Valkey for s
Entire database engineering careers have been spent on a single question: How do you scale an OLTP workload without compromising the system of record that owns the data? Exadata answered the question
qwen4exp: sum the indexer heads by slices (#28023) qwen4exp: sum the indexer heads by slices The head reduction went through a transpose and a sum_rows over ne[1], which left sum_rows with ne0 = 4, on
Grok is very good at agentic tasks! Agentic work is where @grok 4.6 lands hardest, taking the top spot on the Artificial Analysis Agentic Index at 59, tied with Claude Opus 5 Max. The index measures t
model : Granite-Switch Architecture (#25107) granite-switch: add llama.cpp backend (POC, CPU) New 'granite-switch' architecture: a dense, all-attention Granite-4.1 model with N embedded LoRA adapters
I shipped a new feature for my blog today: the Newsletters page, which offers an index of all of the newsletters I've sent out, both my free weekly Substack and my monthly sponsors-only updates. I bui
chat : name tool and argument parser rules by index (#30088) bugfix: infinite recursion caused by a tool named 'call'(#29967) chat : use index for schema and argument rules tests : remove tests tests
arXiv:2610.09920v1 Announce Type: cross Abstract: Prevailing multi-vector visual document retrievers store each page as about a thousand patch vectors, often in vector databases run by a third party.
glm5-next: give dead indexer slots unique scatter rows (#29745) The sparse indexer mask is built with a set_rows scatter. Padded pools, absent sequences and missing tail cells all pointed to the same
arXiv:2609.04391v1 Announce Type: new Abstract: In this work, a novel evaluation scheme built on a generalized variant of the Rand Index measure, namely, the Hullermeier-Rifqi Index, is proposed in or
arXiv:2608.16309v1 Announce Type: cross Abstract: Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipel
sycl : Support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PRE (#26568) support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PREwq update ops.md fix format issue Web
arXiv:2606.24903v1 Announce Type: new Abstract: Deciding when to stop collecting labeled examples is a fundamental but undertheorized problem in applied machine learning. The saturation index S(K) = o
Google’s new Gemini 3.5 Flash is the clear leader on the Intelligence vs Speed Pareto frontier and makes large gains on GDPval-AA (real-world agentic tasks), but is 5x the cost of Gemini 3 Flash @Goog
Full text search is in Public Preview on Pinecone. Check out the bird search demo built by Senior Developer Advocate, Arjun Patel which indexes 2,000 Wikipedia bird articles in one index across four f
Sub-32B open weights models now offer GPT-5 level intelligence with Qwen3.5 27B (Reasoning) matching GPT-5 (medium) at 42 and Gemma 4 31B (Reasoning) matching GPT-5 (low) at 39 on the Artificial Analy
The specific tweet (status/2042207101557342221) is not directly accessible or indexed in search results, and the URL itself appears to be from a future date beyond current indexing. However, based ...