Fankserver
Pinned Loading
Repositories
- dgx-spark-qwen3.6-27b-aeon-bench Public
DGX Spark (GB10) llama-benchy benchmarks: Qwen3.6-27B-AEON — 3 vLLM engines, BF16 vs NVFP4, DSpark-DFlash draft head
fankserver/dgx-spark-qwen3.6-27b-aeon-bench’s past year of commit activity - gfx906-LLM-Inference Public
LLM inference benchmarks, tuning results, and production notes for AMD MI50 (gfx906 / Vega 20) on ROCm — covering Ornith-1.0-35B, Gemma-4-26B, Qwen3.6-35B, MTP, DFlash, EAGLE3, and Docker vs bare-metal comparisons.
fankserver/gfx906-LLM-Inference’s past year of commit activity - llm-glossary Public
Plain-language glossary of LLM & inference-serving terminology (MoE, MLA, DSA, KV cache, speculative decoding, ...)
fankserver/llm-glossary’s past year of commit activity - dgx-spark-nemotron-puzzle-75b-bench Public
DGX Spark (GB10) llama-benchy benchmarks: NVIDIA Nemotron-Puzzle-75B-A9B NVFP4 with MTP speculative decoding on stock vLLM
fankserver/dgx-spark-nemotron-puzzle-75b-bench’s past year of commit activity - dgx-spark-nemotron-120b-bench Public
Benchmarks for NVIDIA Nemotron-3-Super-120B-A12B (NVFP4, hybrid MoE) with vLLM+MTP on a single NVIDIA GB10 / DGX Spark — llama-benchy sweeps, datasets, graphs
fankserver/dgx-spark-nemotron-120b-bench’s past year of commit activity - dgx-spark-qwen3.5-122b-bench Public
Benchmarks for Qwen3.5-122B-A10B (hybrid MoE) with vLLM+DFlash on a single NVIDIA GB10 / DGX Spark — llama-benchy sweeps, datasets, graphs
fankserver/dgx-spark-qwen3.5-122b-bench’s past year of commit activity - vanguard-galaxy-dataexport Public
BepInEx plugin that dumps Vanguard Galaxy's live catalogue (ships, turrets, armor, aspects, factions, conquest ranks) to JSON, plus a Python merger for the wiki's Module:ShipData.
fankserver/vanguard-galaxy-dataexport’s past year of commit activity - bash Public
fankserver/bash’s past year of commit activity - torchapi-performance-tweaker Public
fankserver/torchapi-performance-tweaker’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…