PrototypeCommon
jpezzulli/sglang-rtxpro6000
Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell 96 GB GPU (SM120): 524K context, HiCache and NIXL.
- Owner
- jpezzulli (personal account)
- Stars
- Stars: 189
- Forks
- Forks: 27
- Language
- Python
- License
- Apache-2.0
- Created
- 2026
- Topics
- blackwelldflash2fp8hicachellm-inferencelocal-llmlong-contextnixlnvfp4qwen
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- mubix/cyber-resume-reviewer-skillStars: 189PythonPrototype
- 255308153/CtxGuardStars: 189PythonPrototype
- yuatemycat/SuperGhidraStars: 189PythonPrototype
- marinho/geraldoStars: 189PythonPrototype
- facebookarchive/git-reviewStars: 189PythonPrototype
- mozilla/mozregressionStars: 189PythonPrototype