vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-28 11:49:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
kvcache-ai-ktransformers/archive/ktransformers/optimize/optimize_rules
History
Shaoxu Cheng adcfa9080f
update: Qwen3 MoE model adaptation for NPU (framework) (#1706)
2025-12-11 17:07:57 +08:00
..
npu update: Qwen3 MoE model adaptation for NPU (framework) (#1706) 2025-12-11 17:07:57 +08:00
rocm Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
xpu Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V2-Chat-multi-gpu-4.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V2-Chat-multi-gpu.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V2-Chat.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V2-Lite-Chat-gpu-cpu.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V2-Lite-Chat-multi-gpu.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V2-Lite-Chat.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-amx.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-fp8-linear-ggml-experts-serve-amx.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-fp8-linear-ggml-experts-serve.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-fp8-linear-ggml-experts.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-multi-gpu-4.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-multi-gpu-8.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-multi-gpu-fp8-linear-ggml-experts.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-multi-gpu-marlin.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-multi-gpu.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-npu.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat-serve.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
DeepSeek-V3-Chat.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Glm4Moe-serve.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Internlm2_5-7b-Chat-1m.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Mixtral.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Moonlight-16B-A3B-serve.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Moonlight-16B-A3B.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Qwen2-57B-A14B-Instruct-multi-gpu.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Qwen2-57B-A14B-Instruct.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Qwen2-serve-amx.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Qwen2-serve.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Qwen3Moe-serve-amx.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Qwen3Moe-serve.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Qwen3Next-serve.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00
Smallthinker-serve.yaml Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581) 2025-11-10 17:42:26 +08:00