Saksham Arora · Chimera

Tag: Inference

8 items with this tag.

Oct 01, 2026
Gemini 4 Argon Costs the Same Per Token and Twice Per Task
Sep 28, 2026
Ember-1 Cut 40% of the Tokens and Kept the Score
Sep 19, 2026
CoreWeave Put 16,635 Tokens Per GPU on a Single Rack
Aug 26, 2026
OpenAI's First Chip Wins on Latency, Not FLOPs
Aug 20, 2026
Cerebras CS-4 Shipped a 2 Microsecond Interconnect, and That's the Number That Matters
Jul 13, 2026
GPT-5.6 Beats Claude by 13 Points on One Benchmark, Loses by 16 on Another
Jul 10, 2026
NVIDIA Killed the Draft Model and Got 4x Throughput For Free
Jul 06, 2026
The 518-Token Bug: When GPT-5.5's Reasoning Gets Cut Off at Fixed Intervals

GitHub
LinkedIn
X
Portfolio