Building the IBKR C++ API Client Library, Protobuf Edition
A while back I wrote about building the IBKR C++ API client library on MacOS and Linux/aarch64. Since then, Interactive Brokers has added a Google Protocol B...
Posts by Tag
- c++ 3
- unix 2
- linux 2
- macos 2
- llm 2
- genai 2
- llama 2
- pytorch 1
- cuda 1
- openai 1
- mlx 1
- nvidia 1
- nim 1
- tensorrt‑llm 1
- genai‑perf 1
- benchmark 1
- protobuf 1
c++
Building the IBKR C++ API Client Library
Update: since I wrote this, IBKR has added a protobuf dependency to the C++ API and the build steps below no longer work as-is. I wrote a follow-up post cove...
PyTorch CUDA Extensions
Optimizing Performance with PyTorch CUDA/C++ Extensions: A Deep Dive
unix
Building the IBKR C++ API Client Library, Protobuf Edition
A while back I wrote about building the IBKR C++ API client library on MacOS and Linux/aarch64. Since then, Interactive Brokers has added a Google Protocol B...
Building the IBKR C++ API Client Library
Update: since I wrote this, IBKR has added a protobuf dependency to the C++ API and the build steps below no longer work as-is. I wrote a follow-up post cove...
linux
Building the IBKR C++ API Client Library, Protobuf Edition
A while back I wrote about building the IBKR C++ API client library on MacOS and Linux/aarch64. Since then, Interactive Brokers has added a Google Protocol B...
Building the IBKR C++ API Client Library
Update: since I wrote this, IBKR has added a protobuf dependency to the C++ API and the build steps below no longer work as-is. I wrote a follow-up post cove...
macos
Building the IBKR C++ API Client Library, Protobuf Edition
A while back I wrote about building the IBKR C++ API client library on MacOS and Linux/aarch64. Since then, Interactive Brokers has added a Google Protocol B...
Building the IBKR C++ API Client Library
Update: since I wrote this, IBKR has added a protobuf dependency to the C++ API and the build steps below no longer work as-is. I wrote a follow-up post cove...
llm
Evaluating Llama‑3.3‑70B Inference on NVIDIA H100 and A100 GPUs
Large‑scale language models quickly expose the limits of yesterday’s hardware. To understand how much practical head‑room Hopper offers over Ampere in a prod...
Recent Experiences Debugging with LLMs
I’m frequently asked by clients what my thoughts are on LLMs and coding. Personal experience has informed me that LLMs cannot solve problems of a certain com...
genai
Evaluating Llama‑3.3‑70B Inference on NVIDIA H100 and A100 GPUs
Large‑scale language models quickly expose the limits of yesterday’s hardware. To understand how much practical head‑room Hopper offers over Ampere in a prod...
Recent Experiences Debugging with LLMs
I’m frequently asked by clients what my thoughts are on LLMs and coding. Personal experience has informed me that LLMs cannot solve problems of a certain com...
llama
Evaluating Llama‑3.3‑70B Inference on NVIDIA H100 and A100 GPUs
Large‑scale language models quickly expose the limits of yesterday’s hardware. To understand how much practical head‑room Hopper offers over Ampere in a prod...
Recent Experiences Debugging with LLMs
I’m frequently asked by clients what my thoughts are on LLMs and coding. Personal experience has informed me that LLMs cannot solve problems of a certain com...
pytorch
PyTorch CUDA Extensions
Optimizing Performance with PyTorch CUDA/C++ Extensions: A Deep Dive
cuda
PyTorch CUDA Extensions
Optimizing Performance with PyTorch CUDA/C++ Extensions: A Deep Dive
openai
Recent Experiences Debugging with LLMs
I’m frequently asked by clients what my thoughts are on LLMs and coding. Personal experience has informed me that LLMs cannot solve problems of a certain com...
mlx
Recent Experiences Debugging with LLMs
I’m frequently asked by clients what my thoughts are on LLMs and coding. Personal experience has informed me that LLMs cannot solve problems of a certain com...
nvidia
Evaluating Llama‑3.3‑70B Inference on NVIDIA H100 and A100 GPUs
Large‑scale language models quickly expose the limits of yesterday’s hardware. To understand how much practical head‑room Hopper offers over Ampere in a prod...
nim
Evaluating Llama‑3.3‑70B Inference on NVIDIA H100 and A100 GPUs
Large‑scale language models quickly expose the limits of yesterday’s hardware. To understand how much practical head‑room Hopper offers over Ampere in a prod...
tensorrt‑llm
Evaluating Llama‑3.3‑70B Inference on NVIDIA H100 and A100 GPUs
Large‑scale language models quickly expose the limits of yesterday’s hardware. To understand how much practical head‑room Hopper offers over Ampere in a prod...
genai‑perf
Evaluating Llama‑3.3‑70B Inference on NVIDIA H100 and A100 GPUs
Large‑scale language models quickly expose the limits of yesterday’s hardware. To understand how much practical head‑room Hopper offers over Ampere in a prod...
benchmark
Evaluating Llama‑3.3‑70B Inference on NVIDIA H100 and A100 GPUs
Large‑scale language models quickly expose the limits of yesterday’s hardware. To understand how much practical head‑room Hopper offers over Ampere in a prod...
protobuf
Building the IBKR C++ API Client Library, Protobuf Edition
A while back I wrote about building the IBKR C++ API client library on MacOS and Linux/aarch64. Since then, Interactive Brokers has added a Google Protocol B...