---
title: "Performance"
description: "817 posts about Performance, summarised, each linking to the original."
---

# Performance
> 817 posts about Performance, summarised, each linking to the original.

## Articles

### [Apache Spark Real-Time Mode for Gaming: A Better Way to Do Real-Time Sessionization](https://yomu.fyi/post/apache-spark-real-time-mode-for-gaming-a-better-way-to-do-real-time-se.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Neha Prabhu, Murali Talluri
- Published: Jun 3, 2026
- Type: Tutorial

Gaming platforms need sub-second session data for personalization, recommendations, content scheduling, and operational controls across millions of devices. The described pipeline uses Apache Spark Real-Time Mode with transformWithState to process Kafka events, maintain per-device session state, and emit scheduled heartbeats and timeout events without a separate streaming engine. Events are grouped by deviceId; a StatefulProcessor uses MapState keyed by session ID, while handleInputRows() handles starts and ends and handleExpiredTimer() registers and fires 30-second timers. The implementation was tested at about 500K input events per minute, 4M active sessions, and 8M heartbeat records, producing 16x output amplification. End-to-end latency reached 432 ms at p99, reported as 20x faster than micro-batch mode, and the source states that Real-Time Mode is generally available.


### [Direct Preference Optimization Beyond Chatbots](https://yomu.fyi/post/direct-preference-optimization-beyond-chatbots.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Erick Lachmann, Gabriel Pimenta de Freitas Cardoso, Francisco de Almeida Rocha Alves
- Published: Jun 3, 2026
- Type: Explainer

DharmaOCR applies Direct Preference Optimization (DPO) beyond chat alignment to reduce text degeneration in structured OCR, where outputs are either acceptable transcriptions or failure loops. In a benchmark of Brazilian Portuguese structured-document OCR, vanilla degeneration rates among open-source model families ranged from below 1% to above 33%, while supervised fine-tuning (SFT) did not consistently reach production-acceptable levels. After SFT, the pipeline generated multiple candidates for 23,726 documents, used an automated LLM judge to score them, and retained the model’s degenerate outputs as rejected examples paired with chosen outputs. DPO reduced degeneration in every tested family, by 59.4% on average and up to 87.6%, without reducing extraction quality according to the benchmark; applicability is presented as dependent on failures being categorically identifiable, reliably scoreable, and sufficiently numerous.


### [Stack Benchmarking](https://yomu.fyi/post/stack-benchmarking.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: Ryan Stevens
- Published: Jun 3, 2026
- Type: Benchmark

Ramp’s Stack is an AI-native accounting suite designed to automate repetitive book-closing work, including reconciliations, variance analysis, data entry, and schedules and accruals. To avoid overfitting to individual design partners, Ramp built a benchmark of synthetic business worlds, realistic accounting tasks, and accountant-written grading criteria, including standard and roll-forward worlds for testing memory transfer. The benchmark contains 237 tasks and 3,469 grading criteria in the analyzed slice, and supports repeated runs to compare models, prompts, tools, skills, harness changes, and memory behavior. Optimization included ablating skills, shrinking a spreadsheet skill from 14,000 to 5,000 characters, and tuning the system against end-to-end task performance rather than narrow evaluations. The resulting Stack system achieved the highest agent performance, with 4% higher accuracy and 3% better Pass@1, while remaining on the latency frontier with GPT 5.4; schedules and accruals were harder for raw models than variance analysis.


### [How ClickHouse became fast at joins](https://yomu.fyi/post/how-clickhouse-became-fast-at-joins.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 3, 2026
- Type: Explainer

Over two years, ClickHouse focused on making joins faster for analytical SQL workloads, moving them from a performance gap to a first-class strength. The first year established the foundation with parallel hash joins, local automatic join reordering, filter pushdown, and execution improvements, producing a 4.4× speedup on the TPC-H SF100 join-heavy workload by version 25.4, compared with 22.4. The second year made optimizations effective by default, adding correlated-subquery support, lazy column replication, runtime filters, and statistics-based join reordering. Correlated queries can now run directly, while compact representations avoid copying repeated values and runtime filtering skips rows before hash-table lookups. Across the same benchmark and hardware, these changes delivered another 6× speedup, for a total 26× improvement; one six-table query fell from 3903.7 seconds to 2.7 while peak memory dropped from 99.1 GiB to 3.9 GiB.


### [Holo3.1: Fast & Local Computer Use Agents](https://yomu.fyi/post/holo3-1-fast-local-computer-use-agents.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Maxime Langevin, Hamza Benchekroun, Axel Moyal, Emrick Sinitambirivoutin, Antonio Loison, Avshalom Manevich, Tony Wu, Pierre-Louis Cedoz, Aurélien Lac, Ronan Riochet
- Published: Jun 2, 2026
- Type: Announcement

Holo3.1 is a family of computer-use models released to improve robustness across web, desktop, and mobile environments, agent frameworks, and deployment targets. Based on Qwen, it adds native function-calling alongside structured JSON outputs, expands mobile automation, and offers 0.8B, 4B, 9B, and 35B-A3B sizes for different cost, latency, and performance needs. On AndroidWorld, the 35B-A3B model rises from 67% to 79.3%, while the 4B and 9B variants rise from 58% to 72%; function-calling and native execution achieve near-parity across the stated benchmarks, and Holo3.1 improves more than 25% over Holo3 in the Holotab harness. The release also provides 35B-A3B FP8, Q4 GGUF, and NVFP4 checkpoints for local inference: NVFP4 matches FP8 on OSWorld at about two points below BF16, reaches 1.74 times BF16 token throughput on DGX Spark, and with harness optimizations cuts average step time from 6.8 seconds to 3.3 seconds.


### [Building a .NET API Gateway with ClickHouse and Aspire](https://yomu.fyi/post/building-a-net-api-gateway-with-clickhouse-and-aspire.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 2, 2026
- Type: Tutorial

The tutorial builds a .NET distributed application around a YARP API gateway, two backend APIs, an analytics API, a Blazor dashboard, a load generator, and ClickHouse. Aspire’s AppHost coordinates these resources, injects connection strings and service endpoints, orders startup with dependency health checks, and exposes selected services through stable or external endpoints. The gateway records proxied requests in ClickHouse while emitting OpenTelemetry metrics for request counts, duration, and backend failures. A bounded queue and background ingestion keep request logging off the hot path, while a narrow schema and materialized view precompute minute-level aggregates for volume, p95 latency, error rates, and route comparisons. Aspire supplies live telemetry, whereas ClickHouse retains request history for analytical queries and drill-down into slow requests.


### [TPC-H for less than a cent: ClickHouse Cloud vs. Snowflake, Databricks, BigQuery, and Redshift](https://yomu.fyi/post/tpc-h-for-less-than-a-cent-clickhouse-cloud-vs-snowflake-databricks-bi.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 2, 2026
- Type: Benchmark

ClickHouse Cloud is benchmarked against Snowflake, Databricks, BigQuery, and Redshift on the join-heavy TPC-H workload, with the main comparison using SF100: 100 GB, 866M rows, and 22 queries. Using a single 59-core AWS compute node, the benchmark measures fastest hot runs from three executions with result caching disabled, applies public billing models and comparable Enterprise-tier regional pricing, and publishes scripts, queries, and result files for reproduction. ClickHouse completed SF100 in 19.8 seconds for $0.063 and ranked first on the cost-performance score, while Snowflake Large was faster at 15.9 seconds but cost $0.143; at SF10, ClickHouse ran the workload in 2.9 seconds for $0.009. The results are attributed to two years of join engineering, including faster hash joins, improved planning, correlated subquery support, lazy column replication, runtime filters, and statistics-based join reordering.


### [ClickHouse Release 26.5](https://yomu.fyi/post/clickhouse-release-26-5.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 1, 2026
- Type: Announcement

ClickHouse 26.5 is a monthly release containing 38 new features, 51 performance optimizations, and 224 bug fixes. It reports a record number of performance optimizations and introduces a filesystem table function for running SQL against a local file system. Its main query-planning examples push ORDER BY … LIMIT through eligible LEFT or RIGHT JOINs when the sort key depends only on the preserved side, allowing ClickHouse to limit rows before joining. In a TPC-H benchmark at scale factor 100, enabling this optimization reduced fastest runtime from 1.878 seconds to 0.092 seconds, peak memory from 1.88 GiB to 10.98 MiB, and data read by 1.5×. Additional changes include a GROUP BY … LIMIT shortcut for eligible unordered queries, an experimental in-browser clickhouse-client, and per-subquery query-cache controls.


### [Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains](https://yomu.fyi/post/introducing-mellum2-a-12b-mixture-of-experts-model-by-jetbrains.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Nikita Pavlichenko
- Published: Jun 1, 2026
- Type: Announcement

JetBrains is releasing Mellum2, a 12B-parameter Mixture-of-Experts model trained from scratch on natural language and code. It targets latency-sensitive, high-throughput workloads including routing, retrieval-augmented generation (RAG), summarization, sub-agents, and coding features. The model has 12B total parameters but activates 2.5B per token, with its architecture keeping total capacity high while making inference more efficient for real-time use. Released under the Apache 2.0 license, Mellum2 is described as competitive with similarly sized open models on code generation, reasoning, science, and math benchmarks while delivering more than 2x faster inference. Its text-and-code focus supports high-throughput production workloads and private deployments where proprietary code or internal data may be involved.


### [Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic](https://yomu.fyi/post/beyond-llms-why-scalable-enterprise-ai-adoption-depends-on-agent-logic.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Nicholas Fuller
- Published: Jun 1, 2026
- Type: Explainer

Enterprise workflows are dynamic, long-running, API- and data-rich, and constrained by policies or regulations, creating challenges that an LLM alone may not handle efficiently. The article defines agent logic as software primitives—including knowledge graphs, algorithms, and program-analysis libraries—within an agent harness that steer models toward relevant workflow context. Examples span legacy COBOL and PL/1 understanding, automated test generation, incident investigation and code remediation, and compliance modernization; reported results include ~30× lower token consumption for application understanding, 20–45% higher test coverage, and up to 4.0× better incident-investigation performance than a ReAct baseline. A Condition Insights example reports 57% fewer unsupported claims and 77% lower average token usage, supporting the conclusion that structured guidance can improve quality, cost, and rule adherence.


### [Databricks at SIGMOD 2026](https://yomu.fyi/post/databricks-at-sigmod-2026.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Indrajit Roy
- Published: May 29, 2026
- Type: Announcement

Databricks says its work on Spark Declarative Pipelines will be featured at SIGMOD 2026, where it received an honorable mention award, and that it will attend June 1–5 in Bangalore as a Platinum Sponsor. The announcement describes two mix-and-match incremental programming paths in SDP: materialized views maintained by the Enzyme engine and streaming APIs with stateful operators and watermarks. Enzyme applies incremental view maintenance to ETL, supporting production materialized views with joins, window functions, aggregations, combinations of these patterns, non-deterministic functions such as current\_date(), and AI-specific functions. It also supports Python as well as SQL, detects changes in materialized-view definitions, chooses partition- or row-level updates, selectively caches intermediate results, and uses a cost model based on plan information and prior executions; the post says it outperforms an anonymized competing solution.


### [Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler](https://yomu.fyi/post/profiling-in-pytorch-part-1-a-beginner-s-guide-to-torch-profiler.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Aritra Roy Gosthipaty, Sayak Paul, Sergio Paniego, Rémi Ouazan Reboul, Pedro Cuenca
- Published: May 29, 2026
- Type: Tutorial

The post introduces torch.profiler through a beginner-oriented walkthrough of profiling a matrix multiplication and addition, explaining how to configure the profiler and interpret its outputs. It uses a small function with torch.matmul and torch.add, annotates it with record\_function, captures CPU and CUDA activities after warm-up iterations, and exports a profiler table plus a Chrome trace. The table summarizes event counts and CPU or GPU time, while the trace shows execution order, call hierarchy, CPU-GPU gaps, kernel launches, and overlap. Comparing 64x64 and 4096x4096 matrices demonstrates a shift from overhead-bound behavior to compute-bound behavior; the guide also covers dispatch chains, hidden device-to-device copies, profiler buffer activity, and torch.compile's runtime and caching behavior.


### [Compliance versus conversion: Tax ID validation at checkout](https://yomu.fyi/post/compliance-versus-conversion-tax-id-validation-at-checkout.md)
- Company: [Stripe](https://yomu.fyi/company/stripe.md)
- Author: Jake Estes
- Published: May 29, 2026
- Type: Explainer

Tax ID collection at checkout supports compliant tax invoices and tax determination, including reverse-charge treatment for qualifying cross-border business transactions. Validation can be performed synchronously before purchase completion or asynchronously after checkout: synchronous checks reduce correction and audit risk but may increase abandonment and expose conversion to government-service downtime, while asynchronous checks preserve completion but require follow-up on failures. The implementation discussion covers direct national-registry integrations, third-party validation services, and Stripe’s CheckoutSessions and PaymentIntents integrations, where the Tax ID Element uses verification modes of if\_supported or none. Stripe first applies a country-specific format check, routes validly formatted IDs to government APIs, may fall back to asynchronous processing after four seconds, and exposes status through customer.tax\_id.updated and the customer object.


### [How flat is replacing fat in AWS data center networks](https://yomu.fyi/post/how-flat-is-replacing-fat-in-aws-data-center-networks.md)
- Company: amazon.science
- Author: Giacomo Bernardi, Ratul Mahajan, Seshadhri Comandur
- Published: May 28, 2026
- Type: Problem & solution

Traditional data center networks rely on hierarchical fat-tree topologies, which introduce overhead, upper-layer congestion, and vulnerability to router failures. Although flat random networks theoretically maximize route diversity and resilience, routing computation and cabling complexity historically made them impractical for physical data centers. AWS addressed these constraints by introducing Resilient Network Graphs, a quasi-random architecture powered by a passive optical device called ShuffleBox and a routing algorithm named Spraypoint. Spraypoint sprays packets across random neighbors toward designated waypoints, unlocking twice as many independent paths while operating within commodity router memory limits. Adopted as the default architecture across new AWS facilities, this design reduces router counts by 69%, lowers projected network power consumption by 40%, and increases throughput by up to 33%.


### [How we cut build times by two-thirds by deleting our CMS](https://yomu.fyi/post/how-we-cut-build-times-by-two-thirds-by-deleting-our-cms.md)
- Company: [Sentry](https://yomu.fyi/company/sentry.md)
- Author: Eli Lennox
- Published: May 28, 2026
- Type: Problem & solution

Sentry rebuilt its marketing site and blog of roughly 2,500 pages, replacing a legacy Gatsby setup and traditional headless CMS with Astro, Markdown, Frontmatter, and AI-driven automation. The previous architecture suffered from 14-minute build times, restrictive CMS schema limits, and frequent build failures caused by external API dependencies. A team of 2.5 developers executed the migration in two months using Claude Code agents for data extraction, template translation, and testing. To manage content without a CMS dashboard, Sentry built Claude Skills to guide updates, run local previews, and draft GitHub pull requests. The migration reduced average build times to under 4 minutes, cut broken staging builds by 95 percent, and improved Web Vitals scores from 89 to 97.


### [Open House 2026 Day 2: 10 years of open source and what the ecosystem is building next](https://yomu.fyi/post/open-house-2026-day-2-10-years-of-open-source-and-what-the-ecosystem-i.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: May 28, 2026
- Type: Announcement

Open House 2026 Day 2 recaps ClickHouse’s tenth year as an open-source project and the ecosystem forming around its data platform. The event reported more than 2,600 contributors, nearly 48,000 GitHub stars, over 200 integrations, and the launch of the House Mates partner program. Announcements included Fivetran’s generally available ClickHouse Cloud destination, a Google Cloud Dataflow Pub/Sub template, Sigma’s public-beta connector and ETL Cache Layer, and a ClickHouse dbt Fusion adapter available in alpha through the CLI. The recap also describes MCP and agent-oriented observability work, including a ClickStack MCP server that translates investigations into optimized ClickHouse queries. Internal testing reported up to 25% fewer tool calls, 2.5 times greater consistency, and nearly 20% better evaluation results.


### [BI Serving Pointers; Maximizing for Performance and TCO](https://yomu.fyi/post/bi-serving-pointers-maximizing-for-performance-and-tco.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Chris Koester
- Published: May 27, 2026
- Type: Explainer

BI dashboards can become slow and expensive when teams respond to latency with separate aggregate tables, refresh pipelines, extracts, and tool-specific semantic layers. The post presents Databricks’ BI serving stack from physical storage through Unity Catalog’s governed semantic layer, recommending Gold-layer star schemas, managed tables, liquid clustering, and Predictive Optimization to reduce scanned data and improve query plans. Metric Views centralize KPI definitions and semantic metadata for dashboards, Genie, SQL notebooks, third-party BI tools, and AI agents, while materialization automatically maintains incremental pre-aggregations and routes queries transparently. Additional TCO guidance covers serverless SQL warehouse autoscaling, DBSQL disk and query-result caching, direct lakehouse connections, and system-table monitoring. The stated outcome is compounded lower latency and compute cost, including an observed average 22% performance improvement from Predictive Optimization and sub-second performance from materialized metrics.


### [Thank you for building with us](https://yomu.fyi/post/thank-you-for-building-with-us.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: May 27, 2026
- Type: Announcement

At its 2026 user conference in San Francisco, ClickHouse reports surpassing 4,000 customers and $250 million in annual run-rate revenue, while marking nearly ten years since Alexey Milovidov open-sourced the database. The company attributes its growth to a community of contributors and describes use across AI products, financial services, observability, analytics, and infrastructure. New offerings include ClickHouse Agents, a fully managed agentic analytics service powered by Anthropic’s Claude; CostBench, an open benchmark using each warehouse’s real billing model; and House Mates, a partner program launching with more than 50 partners across six continents. Additional updates include Managed Postgres in public beta, Managed ClickStack and Langfuse for AI-era observability, generally available full-text search, and automatic JOIN optimization, with cost-performance identified as the central constraint for high-concurrency, low-latency workloads.


### [ClickHouse tops $250M ARR and 4,000 customers, launches Claude-powered agents at Open House 2026](https://yomu.fyi/post/clickhouse-tops-250m-arr-and-4-000-customers-launches-claude-powered-a.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: May 27, 2026
- Type: Announcement

At Open House 2026, ClickHouse announced that its serverless cloud offering exceeded $250 million in annual run-rate revenue and reached 4,000 customers, with ARR more than tripling year-over-year and more than 1,000 net new customers added since January. The company launched ClickHouse Agents, a fully managed, no-code agentic analytics service powered by Anthropic’s Claude, with a chat interface, sandboxed code interpreter, artifacts, skills, memory, multi-agent workflows, and MCP-compatible integrations. It also published CostBench, an open benchmark applying each vendor’s real compute billing model to the same workload; ClickHouse Cloud was reported to have 23x better cost-performance than the nearest cloud data warehouse. Other announcements included Managed Postgres in public beta, managed ClickStack, generally available full-text search, cross-region replication, and the House Mates partner program.


### [Reachy Mini goes fully local](https://yomu.fyi/post/reachy-mini-goes-fully-local.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Amir Mahla, Andres Marafioti
- Published: May 27, 2026
- Type: Tutorial

Reachy Mini’s conversation app can now run its speech stack locally instead of sending audio to a server, avoiding cloud, API keys, and data leaving the machine. The tutorial uses speech-to-speech as a cascaded VAD → STT → LLM → TTS pipeline exposed through a Realtime API-compatible /v1/realtime WebSocket, with Silero VAD v5, Parakeet-TDT 0.6B v3, Qwen3-TTS, and a selectable LLM backend. It shows llama.cpp serving Gemma 4 E4B with parallel slots, 64k context, flash attention, and full sliding-window attention, then covers vLLM, MLX, Transformers, hosted Responses API endpoints, and network connection to a wireless robot. Once the backend and app are connected, conversations run through the local loop, while individual stages can be exchanged to trade latency, quality, language coverage, and hardware choices.


[Newer posts](https://yomu.fyi/topic/performance/page/17.md) · [Older posts](https://yomu.fyi/topic/performance/page/19.md)