gpt-oss
damanhduc140902
Pure C++ and HIP inference for gpt-oss on AMD GPUs - no rocBLAS, no RCCL, no MPI. Every kernel, collective and the tokenizer written from scratch. 84,451 tok/s on the 20B and 40,271 on the 120B, on one node of 8x MI250.
Growth over time
1 data points · 2026-10-03 → 2026-10-03How do you feel about this project?
Ask AI about gpt-oss
Question copied to clipboardWhat is the damanhduc140902/gpt-oss GitHub project? Description: "Pure C++ and HIP inference for gpt-oss on AMD GPUs - no rocBLAS, no RCCL, no MPI. Every kernel, collective and the tokenizer written from scratch. 84,451 tok/s on the 20B and 40,271 on the 120B, on one node of 8x MI250.". Written in HIP. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
How to clone gpt-oss
Clone via HTTPS
Clone via SSH
Download ZIP
Download one-for-all.zipFound an issue?
Report bugs or request features on the gpt-oss issue tracker:
Open GitHub Issues