Compare commits
1 Commits
step35/55-
...
step35/67-
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
cb0045960b |
10
README.md
10
README.md
@@ -16,11 +16,11 @@ A 27B model at 128K context with TurboQuant beats a 72B at Q2 with 8K context.
|
||||
See [issues](https://forge.alexanderwhitestone.com/Timmy_Foundation/turboquant/issues) for current progress.
|
||||
|
||||
## Roles
|
||||
- **Strago:** Build spec author
|
||||
- **Cid:** Implementation, benchmarks, deployment
|
||||
- **Locke:** Research support, upstream watch
|
||||
- **John:** Quality review
|
||||
- **Frankie:** Coordination
|
||||
- **Build Spec:** Architecture and specification
|
||||
- **Implementation:** Code, benchmarks, deployment
|
||||
- **Research:** Upstream tracking, literature review
|
||||
- **Quality:** Testing and review
|
||||
- **Coordination:** Project management
|
||||
|
||||
## Source Repos
|
||||
- [TheTom/llama-cpp-turboquant](https://github.com/TheTom/llama-cpp-turboquant) — llama.cpp fork with Metal
|
||||
|
||||
Reference in New Issue
Block a user