Search: github.com/spekulant | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Show HN: Monitor macOS stats and alert upon reaching configurable thresholds (github.com/spekulant)

2 points

a year ago

2.

Show HN: Speculative Decoding from Scratch in PyTorch (2.8x CPU Speedup) (github.com/kunal51107)

4 points

6 months ago

3.

CPU security bugs caused by speculative execution (github.com/marcan)

3 points

8 years ago

4.

Speculative decoding of llama2 models in pure C (github.com/mscheong01)

2 points

2 years ago

5.

Exploring speculation side-channel attacks in Java (github.com/steveloughran)

1 point

8 years ago

6.

Unofficial FAQ on CPU Speculative Execution Bugs (github.com/marcan)

1 point

8 years ago

7.

Ruby port of clojure.spec (github.com/english)

1 point

9 years ago

8.

Omnibox Prerendering coming in Chromium 100 (github.com/WICG)

2 points

4 years ago

9.

Qwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090 (github.com/thc1006)

5 points

a month ago

10.

An implementation of the Speculative Paxos protocol (github.com/UWSysLab)

57 points

10 years ago

11.

Speculative: PoC for speeding-up inference via speculative sampling by ggerganov (github.com/ggerganov)

16 points

3 years ago

12.

X86-64 Speculative Execution Harness (gist.github.com)

4 points

8 years ago

13.

Llama.cpp speculative sampling: 2x faster inference for large models (github.com/ggerganov)

4 points

3 years ago

14.

My speculations writing a coding platform in 8 weeks as a highschooler

4 points

6 years ago

15.

Accelerating LLM Serving with Speculative Inference and Token Tree Verification (github.com/flexflow)

3 points

3 years ago

16.

Cascadeflow: Cut AI API costs 40-85% with speculative model cascading (github.com/lemony-ai)

3 points

7 months ago

17.

Eagle-3 Speculative Decoding for LLM Inference (5.6x speedup) (github.com/SafeAILab)

2 points

a year ago

18.

MLX: Speculative Decoding (github.com/ml-explore)

2 points

2 years ago

19.

BranchFS is a FUSE-based filesystem enables speculative branching for AI agents (github.com/multikernel)

1 point

4 months ago

20.

Speculations on Test-Time Scaling (OpenAI O1 Model) (github.com/srush)

1 point

2 years ago

21.

Speculative Speculative Decoding: Really, Really Fast LLM Inference (github.com/tanishqkumar)

1 point

3 months ago

22.

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding (github.com/facebookresearch)

1 point

2 years ago

23.

Speculate HN: How does OpenAI's GPT Builder work?

1 point

2 years ago

24.

Show HN: Prefetch links on hover and prerender via Speculation Rules API (github.com/midzer)

1 point

3 years ago

25.

Mitigating Speculative Attacks in Crypto (github.com/HACS-workshop)

1 point

8 years ago

26.

Show HN: Handwriter.ttf – Handwriting Synthesis with Harfbuzz WASM (github.com/hsfzxjy)

191 points

2 years ago

27.

Ask HN: What Happened to GitHub's Atom?

59 points

7 years ago

28.

Show HN: Run 500B+ Parameter LLMs Locally on a Mac Mini (github.com/opengraviton)

17 points

3 months ago

29.

Show HN: OpenGraviton – Run 500B+ parameter models on a consumer Mac Mini (opengraviton.github.io)

13 points

3 months ago

30.

Share my pain point: I want dead easy version control.

12 points

14 years ago