numa repositories
Trending repositories tagged numa, ranked by trending score. Updated daily.
-
1
peterosterlund2/texel
Texel chess engine
GitHub · C++ · 67 stars · 5 forks · +1 stars in 24 hours · Trending score 0.45
-
2
k13132/openwrt-dpdk
Data Plane Development Kit (DPDK) integration into OpenWrt
GitHub · Makefile · 39 stars · 15 forks · −1 stars in 24 hours · Trending score 0.10
-
3
exchange-core/collections
High performance and low latency Exchange Collections written in Java
GitHub · Java · 68 stars · 43 forks · 0 stars in 24 hours · Trending score 0.09
-
4
Scottcjn/ram-coffers
LLM infrastructure cost reduction via NUMA-aware weight banking: 147 t/s (8.8x stock llama.cpp) on refurbished enterprise POWER8. Self-hosted inference, no cloud APIs. Part of the Proof of Physical AI stack.
GitHub · Python · 169 stars · 57 forks · −4 stars in 24 hours · Trending score 0.08
-
5
HadrienG2/hwlocality
Rust bindings to Open MPI Portable Hardware Locality "hwloc" library, covering version 2.0 and above.
GitHub · Rust · 56 stars · 9 forks · 0 stars in 24 hours · Trending score 0.07
-
6
guqiong96/Lsglang
Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parallel architecture, suitable for MOE model hybrid inference.
GitHub · Python · 168 stars · 23 forks · 0 stars in 24 hours · Trending score 0.02
-
7
ashvardanian/ForkUnion
Low-latency NUMA-aware fork-join thread-pool with zero allocations, syscalls, CAS, or false-sharing on the hot path for C++, C, Rust, Zig & Mojo 🍴
GitHub · C++ · 385 stars · 27 forks · 0 stars in 24 hours · Trending score 0.02
-
8
yeungtuzi/Xiaotu-LLM
XTU = X Transformers Unity — hybrid (CPU-expert + GPU) inference acceleration for vLLM: mainline plugin + CPU MoE engine (AVX512-VNNI/BF16 MXFP4/FP8), long-prefill GPU streaming, SM80 (A100) port.
GitHub · Python · 16 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00