Popular repositories Loading
-
blackwell-geforce-nvfp4-gemm
blackwell-geforce-nvfp4-gemm PublicNVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.
Python 10
-
NVFP4studio
NVFP4studio PublicAn open-source cross-platform studio for running NVFP4 models locally, featuring a chat interface, OpenAI-compatible API, performance benchmarking, and multilingual support for English, Chinese, an…
Python 2
-
VLLM-TurboQuant-SM120
VLLM-TurboQuant-SM120 PublicBlackwell-ready TurboQuant KV cache compression for Trinity-Large-Thinking on vLLM.
Python 1
-
GGUF-to-NVFP4-SM120
GGUF-to-NVFP4-SM120 PublicLna-Lab production pipeline: GGUF -> modelopt-format NVFP4 + working MTP head for vLLM on RTX PRO 6000 Blackwell (SM120). Stages 2 (NVFP4) and 3 (MTP graft) are Lna-Lab originals; stage 1 (GGUF->bf…
-
Lna-es_for_gemini-cli
Lna-es_for_gemini-cli PublicGame-style operator UI for Gemini CLI | MGS codec-inspired cyberpunk interface with Neo4j conversation graphs
Repositories
- 27b-35b-nvfp4-bench Public
lna-lab/27b-35b-nvfp4-bench’s past year of commit activity - blackwell-geforce-nvfp4-gemm Public
NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.
lna-lab/blackwell-geforce-nvfp4-gemm’s past year of commit activity - DeepGEMM-for-SM120e Public
lna-lab/DeepGEMM-for-SM120e’s past year of commit activity - GGUF-to-NVFP4-SM120 Public
Lna-Lab production pipeline: GGUF -> modelopt-format NVFP4 + working MTP head for vLLM on RTX PRO 6000 Blackwell (SM120). Stages 2 (NVFP4) and 3 (MTP graft) are Lna-Lab originals; stage 1 (GGUF->bf16) reuses li-yifei/gguf-to-nvfp4.
lna-lab/GGUF-to-NVFP4-SM120’s past year of commit activity - Gemma-4-NVFP4-Benchtest Public
lna-lab/Gemma-4-NVFP4-Benchtest’s past year of commit activity - Homemade-10000TPS-Project Public
lna-lab/Homemade-10000TPS-Project’s past year of commit activity - VLLM-TurboQuant-SM120 Public
Blackwell-ready TurboQuant KV cache compression for Trinity-Large-Thinking on vLLM.
lna-lab/VLLM-TurboQuant-SM120’s past year of commit activity - NVFP4studio Public
An open-source cross-platform studio for running NVFP4 models locally, featuring a chat interface, OpenAI-compatible API, performance benchmarking, and multilingual support for English, Chinese, and Japanese.
lna-lab/NVFP4studio’s past year of commit activity - Lna-es_for_gemini-cli Public
Game-style operator UI for Gemini CLI | MGS codec-inspired cyberpunk interface with Neo4j conversation graphs
lna-lab/Lna-es_for_gemini-cli’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…