github.com Apr 01
GitHub - jimliddle/turboquant-amd-vulkan: A TurboQuant implementation with Llama.cpp for AMD with Vulkan runtime
github.com/jimliddle/turboquant-amd-vulkan
Story Details
| Last Updated | |
| Total Articles | 1 |
Main Topics
Similar to This
Previous
AMD FSR upscaling is coming to Xbox Series X|S, PC handhelds, Vulkan and more: AMD is expanding its FSR 4.1 upscaling tech to Xbox Series X|S, PC handhelds ...
neowin.net/news/amd-fsr-upscaling-is-coming-to-xbox-series-xs-pc-handhelds-vulkan-and-more/
github.com Sep 28
vulkan: fuse qwen4exp's SCALE -> SIGMOID -> SCALE -> hc_post chain by fxgsell · Pull Request #29520 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/29520
github.com Aug 27
feat: import qwen4exp (Qwen3.8-Flash-Next) support from upstream PR #27742 by giveen · Pull Request #324 · TheTom/llama-cpp-turboquant
github.com/TheTom/llama-cpp-turboquant/pull/324
Valve funding port of Linux RADV Radeon Vulkan driver to Windows — cross-platform effort already runs 'Counter-Strike 2'
tomshardware.com/software/linux/valve-funding-port-of-linux-radv-radeon-vulkan-driver-to-windows-cross-platform-effort-already-runs-counter-strike-2
github.com Jun 26
vulkan: make TP viable by pwilkin · Pull Request #25051 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an ...
github.com/ggml-org/llama.cpp/pull/25051
github.com May 29
Release b9406 · 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/b9406
Wccftech May 25
Steam Machine Is Close To Release, As System Was Added to Official Vulkan 1.4 Conformant Products With More Specs Details
wccftech.com/steam-machine-close-to-release-vulkan-specs-details/
github.com Apr 14
Release b8786 · 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/b8786
github.com Apr 10
GitHub - Addy-ad/llama-cpp-turbo-planar-iso: Adding Turboquant + Planarquant + Isoquant to llama.cpp
github.com/Addy-ad/llama-cpp-turbo-planar-iso
github.com Apr 07
TurboQuant - Extreme KV Cache Quantization · ggml-org/llama.cpp · Discussion #20969
github.com/ggml-org/llama.cpp/discussions/20969
github.com Apr 03
GitHub - TheTom/llama-cpp-turboquant: LLM inference in C/C++: LLM inference in C/C++. Contribute to TheTom/llama-cpp-turboquant development by creating an ...
github.com/TheTom/llama-cpp-turboquant
nanonets.com Apr 05
Did Google's TurboQuant Actually Solve AI Memory Crunch?: On March 25, 2026, Google Research published a blog post about a compression algorithm called ...
nanonets.com/blog/google-turboquant-ai-memory-crunch/
github.com Mar 31
GitHub - MartinCrespoC/QuantumLeap---Llama.cpp-TurboQuant: 🚀 Run any LLM on any hardware. 130% faster MoE inference with ExpertFlow + TurboQuant KV compression ...
github.com/MartinCrespoC/QuantumLeap---Llama.cpp-TurboQuant
github.com Mar 31
GitHub - quantumaikr/TurboQuant.cpp: turboquant.cpp: turboquant.cpp. Contribute to quantumaikr/TurboQuant.cpp development by creating an account on GitHub.
github.com/quantumaikr/TurboQuant.cpp
github.com Mar 28
GitHub - peva3/turboquant-h2o-streamingllm: Contribute to peva3/turboquant-h2o-streamingllm development by creating an account on GitHub.
github.com/peva3/turboquant-h2o-streamingllm
github.com Mar 26
GitHub - neuromaniacMD/llm-bench: Cross-machine LLM benchmark: Apple Silicon (MLX) vs AMD GPUs (llama.cpp ROCm/Vulkan)
github.com/neuromaniacMD/llm-bench
VideoCardz Feb 21 25
AMD Radeon RX 9070 XT confirmed as 304W card, RX 9070 non-XT is 220W - VideoCardz.com
videocardz.com/newz/amd-radeon-rx-9070-xt-confirmed-as-304w-card-rx-9070-non-xt-is-220w
Valve Engineer's AMD Linux RADV Vulkan driver fix boosted an FSR2 demo sample app by 228% on RDNA 2 GPUs
tomshardware.com/pc-components/gpu-drivers/valve-engineers-amd-linux-radv-vulkan-driver-fix-boosted-an-fsr2-demo-sample-app-by-228-percent-on-rdna-2-gpus
Next