PrototypeCommon
allover326/deepseek-v4-cmp170hx
DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallelism, which vLLM does not support upstream.
- Owner
- allover326 (personal account)
- Stars
- Stars: 118
- Forks
- Forks: 26
- Language
- Python
- License
- Apache-2.0
- Created
- 2026
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- null0526/dario-genesisStars: 118PythonPrototype
- AetherLabsAI/RobotAgentBenchStars: 118PythonPrototype
- Sac-Y/match-cutStars: 118PythonPrototype
- milianw/springer_downloadStars: 118PythonPrototype
- bartTC/django-wakawakaStars: 118PythonPrototype
- danielgtaylor/aristaStars: 118PythonPrototype