Skip to content

Pull requests: TheTom/llama-cpp-turboquant

New pull request New
18 Open 150 Closed
18 Open 150 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fattn-vec: split the turbo K dot at D>128 to stop the VGPR spill (#294) — needs AMD validation CUDA ggml
#295 opened Aug 13, 2026 by TheTom Owner Loading…
sycl, hip: fix two pre-existing build breaks in fork-added code CUDA ggml SYCL
#293 opened Aug 12, 2026 by TheTom Owner Loading…
2
Fix MSVC C2159: duplicate extern from GGML_API on Windows ggml
#292 opened Aug 12, 2026 by sroller Loading…
10
Pr/prefetch weights AMD ZenDNN Apple Metal Ascend NPU conversion CUDA devops documentation Improvements or additions to documentation examples ggml Hexagon IBM zDNN jinja parser model mtmd OpenCL OpenVINO server/ui server SYCL testing vendor Vulkan WebGPU
#291 opened Aug 11, 2026 by giveen • Draft
Pr/metal vulkan v1 AMD ZenDNN Apple Metal Ascend NPU conversion CUDA devops documentation Improvements or additions to documentation ggml Hexagon IBM zDNN jinja parser model mtmd OpenCL OpenVINO server/ui server SYCL testing vendor Vulkan WebGPU
#289 opened Aug 10, 2026 by giveen Loading…
4
Fix determinism leaks in TurboQuant KV cache and WHT state management documentation Improvements or additions to documentation ggml
#281 opened Aug 8, 2026 by giveen Loading…
1
docs : add harness init strided-view bug to coverage limits documentation Improvements or additions to documentation
#278 opened Aug 8, 2026 by giveen Loading…
[ggml-cuda] Compute the turbo4 centroid LUT in advance during the decoding process CUDA ggml
#267 opened Aug 5, 2026 by ghkang-cs Loading…
2
hip: VEC flash-attn for D=512 (Gemma 4) on ROCm with quantized KV ggml Nvidia GPU
#156 opened May 24, 2026 by cclecle Loading…
SYCL Turboquant implementation attempt ggml SYCL
#144 opened May 13, 2026 by cclecle Loading…
2
vulkan: add TurboQuant KV cache support and optimized turbo mat-vec paths ggml Vulkan
#140 opened May 10, 2026 by Fenix46 Loading…
6
fix(qwen35): support Qwen3.5:9B loading from Ollama GGUF model
#135 opened May 8, 2026 by Jordan-HS Loading…
vendor: bump cpp-httplib to 0.43.2 (openssl 4.0.0 fix) python script
#121 opened May 4, 2026 by TheTom Owner Loading…
1 of 3 tasks
1
Turbo dflash examples model python server
#103 opened Apr 23, 2026 by aminya • Draft
7
HIP mixed TurboQuant vec FA on gfx900/gfx906 build ggml Nvidia GPU
#99 opened Apr 21, 2026 by 2bigO Loading…
fix QJL turboquant implementation ggml testing
#77 opened Apr 15, 2026 by zhangsipeng Loading…
1
perf: turbo VEC flash attention — +9% decode on CUDA via autoresearch ggml Nvidia GPU script
#53 opened Apr 4, 2026 by signalnine Loading…
7 tasks done
8
fix: HIP/ROCm compatibility — check cudaMemcpyToSymbol errors, guard … ggml Nvidia GPU
#41 opened Apr 1, 2026 by terrysimons • Draft
2
ProTip! Exclude everything labeled bug with -label:bug.