GitHub - Abzolute1/llama-cpp-optimization-lab: Source patches, experimental methods, and benchmark evidence for local llama.cpp MoE inference optimization.

github.com/Abzolute1/llama-cpp-optimization-lab

Story Details

Last Updated
Total Articles	1

Main Topics

Llama (language model)

#llama-language-model

large language model by Meta AI

Laboratory

#laboratory

facility that provides controlled conditions in which scientific or technological research, experiments, and measurement may be performed

Experiment

#experiment-67383d866de70

scientific procedure carried out to support, refute, or validate a hypothesis

Similar to This

github.com 5h

qwen4exp : build the QSA selection without the kq_mask by sanmai · Pull Request #30965 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30965

0 similar articles

github.com Oct 22

llama : add adaptive single-graph MoE offload by pwilkin · Pull Request #30971 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30971

0 similar articles

github.com Oct 22

GitHub - heterodoxin/AbliteratedOutTheBox: llama.cpp fork that abliterates at inference

github.com/heterodoxin/AbliteratedOutTheBox

0 similar articles

github.com Oct 21

llama: create new fused op for QSA mask by am17an · Pull Request #30640 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30640

0 similar articles

github.com Oct 22

webgpu : add Q2_0 support by teddygood · Pull Request #30914 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30914

0 similar articles

github.com Oct 21

models: Add Flint model (FlintForCausalLM) by alexey-rsi · Pull Request #30928 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30928

0 similar articles

github.com Oct 17

CUDA: faster MMVQ for low-bit types by am17an · Pull Request #30517 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30517

0 similar articles

VentureBeat

Credibility C

Oct 15

NVIDIA's Nemotron 3.5 Super VL with post-training beats Claude Opus 5, GPT-6.1 Sol on specialized task benchmarks

venturebeat.com/technology/nvidias-new-open-nemotron-3-5-super-vl-with-post-training-beats-claude-opus-5-gpt-6-1-sol-on-specialized-task-benchmarks

6 similar articles

0 1

github.com Oct 16

cpu : reduce AVX2 tiled accumulators together by trivalik · Pull Request #30296 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30296

0 similar articles

github.com Oct 14

common : add --spec-draft-n-ubatch by ggerganov · Pull Request #30459 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/30459

0 similar articles

github.com Oct 10

[Model] Support MiniCPM-V 4.7 by tc-mb · Pull Request #29416 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/29416

0 similar articles

github.com Sep 03

GitHub - mihailescu2m/llama.cpp: LLM inference in C/C++: LLM inference in C/C++. Contribute to mihailescu2m/llama.cpp development by creating an account on ...

github.com/mihailescu2m/llama.cpp

0 similar articles

github.com Aug 23

GitHub - oussemah/llama.cpp at moe-cache-ousemma: LLM inference in C/C++. Contribute to oussemah/llama.cpp development by creating an account on GitHub.

github.com/oussemah/llama.cpp/tree/moe-cache-ousemma

0 similar articles

github.com Aug 19

llama : add --n-cpu-ffn option by John-194 · Pull Request #26622 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/26622

0 similar articles

github.com Jul 12

GitHub - eramax/glm-5.2-for-3090: Research repo compressing GLM-5.2 MoE experts for RTX 3090: 79 experiments, trainable codecs, 75-layer pipeline ...

github.com/eramax/glm-5.2-for-3090

0 similar articles

github.com Jul 09

ggml-hip: enable -funsafe-math-optimizations (#24668) · ggml-org/llama.cpp@ccb0c34

github.com/ggml-org/llama.cpp/commit/ccb0c3422394fbbfc28fd91f8c77111b748cfa09

2 similar articles

github.com Jun 13

Add arch support for cohere2-MoE by michaelw9999 · Pull Request #24260 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/24260

0 similar articles

github.com Apr 03

(revert) kv-cache : do not quantize SWA KV cache by ggerganov · Pull Request #21332 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/21332

0 similar articles

github.com Mar 29

Optimize MOE GEMV kernel for BS > 1. by gaugarg-nv · Pull Request #20905 · ggml-org/llama.cpp

github.com/ggml-org/llama.cpp/pull/20905

0 similar articles

github.com Feb 09

Release b7973 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.

github.com/ggml-org/llama.cpp/releases/tag/b7973

0 similar articles