| .. |
|
DeepSeek-V2-Chat-multi-gpu-4.yaml
|
update yaml example; update version idx; update docker file
|
2024-08-29 22:39:20 +08:00 |
|
DeepSeek-V2-Chat-multi-gpu.yaml
|
update yaml example; update version idx; update docker file
|
2024-08-29 22:39:20 +08:00 |
|
DeepSeek-V2-Chat.yaml
|
fix readme; adjust param
|
2024-08-29 10:40:08 +08:00 |
|
DeepSeek-V2-Lite-Chat-multi-gpu.yaml
|
[feature] release 0.1.3
|
2024-08-28 16:11:43 +00:00 |
|
DeepSeek-V2-Lite-Chat.yaml
|
wjh-change
|
2024-11-04 14:02:19 +08:00 |
|
DeepSeek-V3-Chat-fp8-linear-ggml-experts.yaml
|
Add data loader to read special weights for fp8; Add special weight process script
|
2025-02-24 11:34:17 +00:00 |
|
DeepSeek-V3-Chat-multi-gpu-4.yaml
|
toy support for experts on GPU, no CUDA Graph
|
2025-02-15 15:16:00 +00:00 |
|
DeepSeek-V3-Chat-multi-gpu-8.yaml
|
toy support for experts on GPU, no CUDA Graph
|
2025-02-15 15:16:00 +00:00 |
|
DeepSeek-V3-Chat-multi-gpu-marlin.yaml
|
update marlin expert example
|
2025-02-12 04:11:00 +00:00 |
|
DeepSeek-V3-Chat-multi-gpu.yaml
|
⚡ ready to publish
|
2025-02-10 12:29:23 +08:00 |
|
DeepSeek-V3-Chat.yaml
|
⚡ ready to publish
|
2025-02-10 12:29:23 +08:00 |
|
Internlm2_5-7b-Chat-1m.yaml
|
[feature] release 0.1.3
|
2024-08-28 16:11:43 +00:00 |
|
Mixtral.yaml
|
typo fix: KMisrtal -> KMistral
|
2024-09-12 15:58:01 +00:00 |
|
Qwen2-57B-A14B-Instruct-multi-gpu.yaml
|
[feature] release 0.1.3
|
2024-08-28 16:11:43 +00:00 |
|
Qwen2-57B-A14B-Instruct.yaml
|
[fix] bugs about Qwen57B, install requirement, Dockerfile
|
2024-08-30 09:51:32 +00:00 |
