llama-cpp-p100-patches

llama.cpp performance patches developed and measured on Tesla P100 (GP100, sm_60). Most are not Pascal-specific.

shinbunbun/llama-cpp-p100-patches

View on GitHub ↗

llama.cpp performance patches developed and measured on Tesla P100 (GP100, sm_60). Most are not Pascal-specific.

llama-cpp-p100-patches ranks 320th of 343 in Inference Optimization, last commit 25 days ago.

Star trajectory

25 days tracked
2026-10-2866 stars today2026-11-22
Momentum

- in 30d, below the Inference Optimization median of +1.6%.

Maintenance

Last commit 25 days ago, staler than the median of 16d.

How it compares in Inference Optimization

llama-cpp-p100-patches
66
stars
- 30d
commit 25 days ago
Inference Optimization median
242
stars
+1.6% 30d
commit ~16d ago
Leader · supertonic
13.8k
stars
-0.1% 30d
commit 74 days ago

Ranked 320th of 343 by stars.

Ranked by shared tags, then keywords, then stars
  1. LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50…

    Committed 5d ago · C++ · AGPL-3.0

    Shares Inference Optimization, GPU Kernels

  2. Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU…

    +36 (+6.6%) in 30d · Committed 3d ago · Sass · Apache-2.0

    Shares Inference Optimization, GPU Kernels

  3. lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.

    +43 (+14%) in 30d · Committed 31d ago · Python · Apache-2.0

    Shares Inference Optimization, GPU Kernels

  4. Rust + CUDA inference engine for NVIDIA RTX PRO 6000 Blackwell and RTX 5090. Serves safetensors and GGUF over…

    +37 (+13%) in 30d · Committed today · OpenEdge ABL · MIT

    Shares Inference Optimization, GPU Kernels

  5. OrbitKV is a High Performance KV Cache System for LLM Inference.

    -52 (-15%) in 30d · Committed yesterday · Rust · Apache-2.0

    Shares Inference Optimization, GPU Kernels

  6. Sparse Inferencing for transformer based LLMs

    +1 (+0.5%) in 30d · Committed 242d ago · Python · Apache-2.0

    Shares Inference Optimization, GPU Kernels

  7. Tiny ASIC implementation for "The Era of 1-bit LLMs All Large Language Models are in 1.58 Bits" matrix…

    +0 (+0.0%) in 30d · Committed 946d ago · Verilog · Apache-2.0

    Shares Inference Optimization, GPU Kernels

  8. Hand-written NVFP4 W4A16 CUDA kernels for Volta

    +13 (+7.4%) in 30d · Committed 94d ago · Python · Other license

    Shares Inference Optimization, GPU Kernels

  9. An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and…

    +9 (+5.7%) in 30d · Committed 65d ago · Python · MIT

    Shares Inference Optimization, GPU Kernels

  10. [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

    +2 (+1.4%) in 30d · Committed 816d ago · Scala · MIT

    Shares Inference Optimization, GPU Kernels

Language
Nix
License
MIT License
Contributors
1
Forks
6
Watchers
6
Open issues
0
Releases
0
Created
2026-08-03
Stars this week
+2

You've seen where llama-cpp-p100-patches stands today.

Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain llama-cpp-p100-patches?

Claim this page to add your own call-to-action.

Claim this page