Skip to content

Commit 038bd92

Browse files
committed
blog: add predicted-latency based scheduling for LLMs
Signed-off-by: kaushikmitr <kaushikmitra.umd@gmail.com>
1 parent bfb01a5 commit 038bd92

20 files changed

Lines changed: 503 additions & 2 deletions

blog/2026-03-13_predicted-latency-based-scheduling-for-llms.md

Lines changed: 473 additions & 0 deletions
Large diffs are not rendered by default.

blog/authors.yml

Lines changed: 19 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -128,6 +128,24 @@ tushargohad:
128128

129129
guymargalit:
130130
name: Guy Margalit
131-
title: Senior Technical Staff Member, IBM Storage CTO Ofiice
131+
title: Senior Technical Staff Member, IBM Storage CTO Office
132132
url: https://www.linkedin.com/in/guymargalit/
133133
image_url: /img/blogs/guymargalit.webp
134+
135+
kaushikmitra:
136+
name: Kaushik Mitra
137+
title: Software Engineer, Google
138+
url: https://github.com/kaushikmitr
139+
image_url: https://avatars.githubusercontent.com/u/157416163?v=4
140+
141+
benjaminbraun:
142+
name: Benjamin Braun
143+
title: Software Engineer, Google
144+
url: https://github.com/BenjaminBraunDev
145+
image_url: https://avatars.githubusercontent.com/u/187570160?v=4
146+
147+
abdullahgharaibeh:
148+
name: Abdullah Gharaibeh
149+
title: Senior Staff Software Engineer, Google
150+
url: https://github.com/ahg-g
151+
image_url: https://avatars.githubusercontent.com/u/40361897?v=4

blog/tags.yml

Lines changed: 11 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -87,4 +87,14 @@ kv-cache:
8787
storage:
8888
label: Storage
8989
permalink: /storage
90-
description: Storage related content
90+
description: Storage related content
91+
92+
scheduling:
93+
label: Scheduling
94+
permalink: /scheduling
95+
description: Request scheduling and load balancing for LLM inference
96+
97+
inference:
98+
label: Inference
99+
permalink: /inference
100+
description: LLM inference serving and optimization
49.3 KB
Loading
154 KB
Loading
235 KB
Loading
218 KB
Loading
229 KB
Loading
201 KB
Loading
245 KB
Loading

0 commit comments

Comments
 (0)