ProblemNest
Sign In
You are coding as a Guest. Sign in with Google in 1 tap to save your daily streak, lock in +50 XP & boost your college rank!
Save Streak (1-Tap Google)
9:00 AM Daily Incident ReleaseMaintaining a 7-day streak grants a 2.5× Recruiter Visibility Multiplier on the Recruiter Talent Radar.
Multiplier Ladder:1d: 1.0ו3d: 1.5ו7d: 2.5× MAX
🔥Stable Softmax & Temperature (LLM Sampling)Medium
DAILY PROBLEM OF THE DAY+50 XP • Daily Streak

Solve today's challenge or tackle one of the 3 Super Hard challenges for +150 XP.

MediumAI & Machine Learning•Acceptance: 58.1%

Stable Softmax & Temperature (LLM Sampling)

Targeted in FAANG & Tech OA:GoogleAmazonMicrosoftSwiggy
Real-World Engineering Context
Directly implements the final token sampling layer of ChatGPT and Llama-3, translating raw transformer unnormalized log-probabilities into categorical next-token predictions.
Given a 1D array of float `logits` and a positive `temperature`, compute the numerically stable Softmax probability distribution. Each element should be rounded to 4 decimal places: $$P(i) = \frac{\exp((\text{logits}[i] - \max(\text{logits})) / T)}{\sum_j \exp((\text{logits}[j] - \max(\text{logits})) / T)}$$

Sample Test Cases

Input: [[10,10],1]
Expected: [0.5,0.5]
Input: [[1000,1000],1]
Expected: [0.5,0.5]

Constraints

  • 1 <= logits.length <= 1000
  • -1000.0 <= logits[i] <= 1000.0
  • 0.1 <= temperature <= 5.0
Verified Proof-of-Work ATS PortfolioCryptographic Verification
Export tamper-proof problem verifications to your direct ATS applications
DevScore: Unranked (0/1000)

Every verified problem solve writes authentic cryptographic proof-of-work to your profile. Attach your verified DevScore badge to ATS applications to stand out to engineering hiring teams across 4,000+ verified live tech openings (23,000+ cumulative audited) on RoleNest.

Explore 4,000+ Direct ATS Openings on RoleNest ↗Solve Challenge to Activate Ledger