corpus.blog
43,567 blogs · 5,563,491 posts Claim your blog
Record · corpus.blog/posts/01a0f044-89e3-725a-a9be-6b86190e9940

Quail: Speeding up AI-SQL by jointly optimizing query planner and inference engine

Modal · published 24 September 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at modal.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
48
Words captured
4,036

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://x.com/karpathy/status/2102124533729955960?s=20
x.com
https://x.com/mattdesl/status/2100899669802963060?s=20
x.com
https://typesafe.ai/
typesafe.ai
Typesafe AI: System One Models and Jev
typesafe.ai
https://docs.snowflake.com/en/user-guide/snowflake-cortex/aisql
docs.snowflake.com
https://github.com/fsdatalab/quail
github.com
https://github.com/fsdatalab/quail-bench
github.com
https://arxiv.org/abs/2402.05099
arxiv.org
https://flashinfer.ai/2024/02/02/cascade-inference.html
flashinfer.ai
https://fsdatalab.github.io/
fsdatalab.github.io
https://fsdatalab.github.io/blog/introducing-quail/
fsdatalab.github.io
https://fsdatalab.github.io/quail/docs
fsdatalab.github.io
https://arxiv.org/html/2408.05109v4
arxiv.org
https://docs.databricks.com/aws/en/large-language-models/ai-functions
docs.databricks.com
https://cloud.google.com/blog/products/data-analytics/sql-reimagined-for-the-ai-era-with-bigquery-ai-functions
cloud.google.com
https://github.com/KarelDO/BioDEX
github.com
https://dl.acm.org/doi/10.1145/3685980.3685984
dl.acm.org
https://www.youtube.com/watch?v=iJhRbDFJjbg
youtube.com
https://github.com/tobymao/sqlglot
github.com
https://substrait.io/
substrait.io
https://github.com/apache/arrow
github.com
https://dsf.berkeley.edu/jmh/miscpapers/sigmod93.pdf
dsf.berkeley.edu
https://dl.acm.org/doi/10.1145/320455.320457
dl.acm.org
https://people.eecs.berkeley.edu/~kubitron/cs252/handouts/papers/RooflineVyNoYellow.pdf
people.eecs.berkeley.edu
https://github.com/fsdatalab/quail/blob/main/quail/cost/sol.py
github.com
https://github.com/marcelroed/gigatoken
github.com
https://github.com/deepseek-ai/DeepGEMM
github.com
https://github.com/dao-ailab/flash-attention
github.com
https://github.com/triton-lang/triton
github.com
Flash-Decoding for long-context inference Read at the source ↗
pytorch.org
https://arxiv.org/abs/2406.17276
arxiv.org
https://www.lmsys.org/blog/2026-06-15-next-generation-speculative-decoding-dflash-v2/
lmsys.org
https://www.lmsys.org/blog/2025-09-10-sglang-hicache/
lmsys.org
https://github.com/redis/redis
github.com
https://github.com/duckdb/duckdb
github.com
https://hazyresearch.stanford.edu/blog/2025-09-28-tp-llama-main
hazyresearch.stanford.edu
https://docs.nvidia.com/cuda/cuda-programming-guide/04-special-topics/programmatic-dependent-launch.html
docs.nvidia.com
https://db.in.tum.de/~kersten/Tidy%20Tuples%20and%20Flying%20Start%20Fast%20Compilation%20and%20Fast%20Execution%20of%20Relational%20Queries%20in%20Umbra.pdf
db.in.tum.de
https://arxiv.org/abs/2209.05310
arxiv.org
A declaration on math and AI
mathandai.org
https://arxiv.org/abs/2605.06068
arxiv.org
https://github.com/apache/datafusion
github.com
https://x.com/ekzhang1/status/2089507697930678419?s=20
x.com
https://github.com/GeeeekExplorer/nano-vllm
github.com
https://github.com/sgl-project/mini-sglang
github.com
https://jbarrow.ai/about/
jbarrow.ai
https://doubleword.ai/
doubleword.ai
https://fergusfinn.com/
fergusfinn.com
Elsewhere on modal.com (15)
https://modal.com/llm-almanac/workloads
modal.com
Host overhead is killing your inference efficiency Read at the source ↗
modal.com
'I paid for the whole GPU, I am going to use the whole GPU': A high-level guide to GPU utilization Read at the source ↗
modal.com
https://modal.com/gpu-glossary/perf/arithmetic-intensity
modal.com
https://modal.com/gpu-glossary/perf/arithmetic-bandwidth
modal.com
https://modal.com/gpu-glossary/device-hardware/tensor-core
modal.com
How to serve trillions of tokens for trillion-parameter coding agents Read at the source ↗
modal.com
Achieve state-of-the-art inference latencies with speculative decoding Read at the source ↗
modal.com
https://modal.com/gpu-glossary/perf/memory-bandwidth
modal.com
Speculation Is All You Need Read at the source ↗
modal.com
https://modal.com/docs/guide/volumes
modal.com
https://modal.com/gpu-glossary/perf/peak-rate
modal.com
https://modal.com/gpu-glossary/perf/performance-bottleneck
modal.com
https://modal.com/llm-almanac/spec-dec-roofline
modal.com
Boosting multimodal inference performance by >10% with a single Python dictionary Read at the source ↗
modal.com