Parsa Ahmadnezhad

🛟 Introducing Floaty for @float_financial > me and @4derekwang went to the Susa x KP event > thought about panel talk on: Execution > Idea > decided to execute in 24 hrs > researched and built an MCP over Float API with 60+ tools shoutout @anirudhbv_ce @gtskeg @shaheersan

Parsa and I ran into @dwarkesh_sp in the lobby LOL! I told him that I loved his podcast episode with Jensen Huang. Can't wait for the next episode :)

@anirudhbv_ce @agihouse_org @Waymo @SebastianThrun @blelbach Time to add sf to bio 🔥🔥

Today, I demo'd turboquant-gpu at @agihouse_org in Hillsborough. The founder of @Waymo asked me about the next steps and where I'll take it. I said I'll show him in two weeks and took his email. Stay tuned. Super super excited for what's coming. ✌️

@byjustinwu @Tesla 🔥🔥🔥

joining @Tesla in hawthorne, california this fall :)

@anirudhbv_ce @Shopify @fnthawar good stuff bv ce

I presented TurboQuant-GPU at @Shopify Toronto today :) Had a blast talking about KV cache compression and discussing future implementations for agents 🔥 Thank you @fnthawar for inviting me and hosting the talk today 🙏 pip install turboquant-gpu ✌️ ( 1.4k downloads!! )

@victorgu0 @anirudhbv_ce bv ce

which waterloo kid should i do next lol

@nengjiali goat back at it 🔥

I spent 4 brutal months building a full Stereo Visual SLAM system from scratch in C++17 + CUDA. NO pre-made libraries. NO black-box magic. I just wanted to understand the underlying mechanics behind SLAM. Here’s the intuitive breakdown (the full SLAM pipeline, the math that almost broke me, and the real KITTI footage)👇 cc @aelluswamy your work in this space is a massive inspiration for tackling this from absolute scratch

A mains-powered isolated phone charger that I designed fully from discrete analog logic: - Offline isolated flyback topology, 15W of USB output - Custom discrete type II compensation loop - Compensated for 62° phase of margin and 12 dB of gain margin - Schmitt trigger integrator ramp generator + comparator-based PWM control - Designed for IEC 62368-1/CISPR compliance

@anirudhbv_ce @huggingface abv ce strikes again 📈

pip install turboquant-gpu 5.02x KV cache compression for ANY GPU (RTX, H100, A100, B200) - works over @huggingface transformers - dead-simple API: compress + generate in 3 lines - 3-bit Lloyd-Max fused KV compression (0.98 cosine similarity) - outperforms MXFP4 (3.76x) and NVFP4 (3.56x) on compression Ran Mistral-7B: 1,408 KB → 275 KB KV cache (5.02x) Quickstart: github.com/DevTechJr/turb… Written in cuTile (CUDA 12, 13) with PyTorch fallbacks

Horizon is finally here. Connect claude or poke to give them access to your d2l and piazza. Lock in now (horizon.hamzaammar.ca/onboard)

@HamzakAmmar @kavir777 clutch 🔥🔥

@anirudhbv_ce @GoogleResearch @nvidia

I implemented @GoogleResearch's TurboQuant as a CUDA-native compression engine on Blackwell B200. 5x KV cache compression on Qwen 2.5-1.5B, near-loseless attention scores, generating live from compressed memory. 5 custom cuTile CUDA kernels ft: - fused attention (with QJL corrections) - online softmax -on-chip cache decompression - pipelined TMA loads Try it out: devtechjr.github.io/turboquant_cut… s/o @blelbach and the cuTile team at @nvidia for lending me Blackwell GPU access :) cc @sundeep @GavinSherry

Finally got my Softmax kernels running on a @nvidia Blackwell B300 today! A single-pass tiled Softmax and a two-pass streaming Online Softmax. Writing ct.load() feels like cheating compared to manual Triton pointer math when mapping directly to TMA hardware.

@byjustinwu @lucashjin you gotta open up the waitlist I gotta sign up for that asap

@parsaxa @lucashjin wait how'd u know...

we built git for video editing. edit in parallel inside davinci resolve.

@lucashjin 🔥🔥 @Adobe

we just built git for video editing.

@_rickytang @WisprFlow @excalidraw thank you man ❤️‍🔥🫡

@parsaxa @WisprFlow @excalidraw thanks parsa! floaty is sickk asw :)

we built @WisprFlow for @excalidraw 👇 yapdraw.vercel.app