llama.cpp/.github/workflows
Rémy Oudompheng 66ee4f297c
vulkan: implement initial support for IQ2 and IQ3 quantizations (#11360)
* vulkan: initial support for IQ3_S

* vulkan: initial support for IQ3_XXS

* vulkan: initial support for IQ2_XXS

* vulkan: initial support for IQ2_XS

* vulkan: optimize Q3_K by removing branches

* vulkan: implement dequantize variants for coopmat2

* vulkan: initial support for IQ2_S

* vulkan: vertically realign code

* port failing dequant callbacks from mul_mm

* Fix array length mismatches

* vulkan: avoid using workgroup size before it is referenced

* tests: increase timeout for Vulkan llvmpipe backend

---------

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
2025-01-29 18:29:39 +01:00
..
bench.yml.disabled ggml-backend : add device and backend reg interfaces (#9707) 2024-10-03 01:49:47 +02:00
build.yml vulkan: implement initial support for IQ2 and IQ3 quantizations (#11360) 2025-01-29 18:29:39 +01:00
close-issue.yml ci : fine-grant permission (#9710) 2024-10-04 11:47:19 +02:00
docker.yml ci : fix build CPU arm64 (#11472) 2025-01-29 00:02:56 +01:00
editorconfig.yml ci : pin dependency to specific version (#11137) 2025-01-08 12:07:20 +01:00
gguf-publish.yml ci : update checkout, setup-python and upload-artifact to latest (#6456) 2024-04-03 21:01:13 +03:00
labeler.yml labeler.yml: Use settings from ggerganov/llama.cpp [no ci] (#7363) 2024-05-19 20:51:03 +10:00
python-check-requirements.yml py : fix requirements check '==' -> '~=' (#8982) 2024-08-12 11:02:01 +03:00
python-lint.yml ci : add ubuntu cuda build, build with one arch on windows (#10456) 2024-11-26 13:05:07 +01:00
python-type-check.yml ci : reduce severity of unused Pyright ignore comments (#9697) 2024-09-30 14:13:16 -04:00
server.yml tests : increase timeout when sanitizers are enabled (#11300) 2025-01-19 20:22:30 +02:00