We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent de1838f commit 63161b4Copy full SHA for 63161b4
docs/GPULlama3_ROADMAP.md
@@ -2,9 +2,9 @@
2
3
- [Pending Merge] **LangChain4j integration**
4
- [ ] **Additional quantization formats**
5
- - [ ] Q8
+ - [x] Q8
6
- [ ] Q4
7
- - [ ] INT8 native support for GPUs
+ - [x] INT8 native support for GPUs
8
- [ ] **Additional architectures and model format**
9
- [x] Mistral/Mixtral models
10
- [x] Qwen
@@ -20,5 +20,4 @@
20
- [ ] **Performance optimizations**
21
- [ ] Multi-GPU support
22
- [X] Memory-efficient attention mechanisms
23
- - [ ] More Kernel fusion improvements
24
-- [ ] **GraalVM Native Image**
+ - [x] More Kernel fusion improvements
0 commit comments