vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-10-07 23:30:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
All workflows kcpp-build-release-linux-cu13.yaml kcpp-build-release-linux-oldpc.yaml kcpp-build-release-linux-rocm.yaml kcpp-build-release-linux.yaml kcpp-build-release-macos.yaml kcpp-build-release-win-oldpc.yaml kcpp-build-release-win.yaml test-autoguess.yaml test-unofficial-arm64.yaml test-unofficial-linux-olderpc.yaml test-unofficial-win-olderpc.yaml test-unofficial-win-oldpc-avx2.yaml
Actor
All actors vrr
Status
All status Success Failure Waiting Running
ggml-webgpu: fix flash_attn supports_op check for overlapping KV (#28205)
update-ops-docs.yml #482 -Commit 36a73916ee pushed by vrr
upstream
2026-10-07 21:27:18 +00:00
0s
ggml-webgpu: fix flash_attn supports_op check for overlapping KV (#28205)
python-type-check.yml #481 -Commit 36a73916ee pushed by vrr
upstream
2026-10-07 21:27:11 +00:00
0s
ggml-webgpu: fix flash_attn supports_op check for overlapping KV (#28205)
python-check-requirements.yml #480 -Commit 36a73916ee pushed by vrr
upstream
2026-10-07 21:27:00 +00:00
0s
ggml-webgpu: fix flash_attn supports_op check for overlapping KV (#28205)
pre-tokenizer-hashes.yml #479 -Commit 36a73916ee pushed by vrr
upstream
2026-10-07 21:26:52 +00:00
0s
common : fix HF cache paths on Windows (#29475)
update-ops-docs.yml #478 -Commit 6c7a87f7e5 pushed by vrr
upstream
2026-09-30 01:34:57 +00:00
0s
common : fix HF cache paths on Windows (#29475)
python-type-check.yml #477 -Commit 6c7a87f7e5 pushed by vrr
upstream
2026-09-30 01:34:56 +00:00
0s
common : fix HF cache paths on Windows (#29475)
pre-tokenizer-hashes.yml #476 -Commit 6c7a87f7e5 pushed by vrr
upstream
2026-09-30 01:34:56 +00:00
0s
cuda : add conv3d with implicit GEMM (#29137)
update-ops-docs.yml #475 -Commit 53ed051ce5 pushed by vrr
upstream
2026-09-25 19:35:12 +00:00
0s
cuda : add conv3d with implicit GEMM (#29137)
python-type-check.yml #474 -Commit 53ed051ce5 pushed by vrr
upstream
2026-09-25 19:35:06 +00:00
0s
cuda : add conv3d with implicit GEMM (#29137)
pre-tokenizer-hashes.yml #473 -Commit 53ed051ce5 pushed by vrr
upstream
2026-09-25 19:35:07 +00:00
0s
cuda : tune MMVQ to MMQ crossover for SM70 (Volta) (#28912)
update-ops-docs.yml #472 -Commit 68d9053afd pushed by vrr
upstream
2026-09-22 19:34:55 +00:00
0s
cuda : tune MMVQ to MMQ crossover for SM70 (Volta) (#28912)
python-type-check.yml #471 -Commit 68d9053afd pushed by vrr
upstream
2026-09-22 19:34:54 +00:00
0s
ggml-cpu: add F16 input to the FWHT (#27779)
update-ops-docs.yml #470 -Commit 4fea119de3 pushed by vrr
upstream
2026-09-20 01:34:44 +00:00
0s
ggml-cpu: add F16 input to the FWHT (#27779)
python-type-check.yml #469 -Commit 4fea119de3 pushed by vrr
upstream
2026-09-20 01:34:43 +00:00
0s
ggml-cpu: add F16 input to the FWHT (#27779)
python-check-requirements.yml #468 -Commit 4fea119de3 pushed by vrr
upstream
2026-09-20 01:34:45 +00:00
0s
ggml-cpu: add F16 input to the FWHT (#27779)
pre-tokenizer-hashes.yml #467 -Commit 4fea119de3 pushed by vrr
upstream
2026-09-20 01:34:45 +00:00
0s
ggml-cpu: add F16 input to the FWHT (#27779)
copilot-setup-steps.yml #466 -Commit 4fea119de3 pushed by vrr
upstream
2026-09-20 01:34:44 +00:00
0s
hexagon: add back missing contiguous fast-path and hvx_copy_uu for each run (#28886)
update-ops-docs.yml #465 -Commit 930e2fa599 pushed by vrr
upstream
2026-09-17 07:34:28 +00:00
0s
hexagon: add back missing contiguous fast-path and hvx_copy_uu for each run (#28886)
python-type-check.yml #464 -Commit 930e2fa599 pushed by vrr
upstream
2026-09-17 07:34:27 +00:00
0s
qwen4exp: enable rms_norm + mul fusion (#28896)
python-type-check.yml #463 -Commit 41abbfd599 pushed by vrr
upstream
2026-09-15 19:34:28 +00:00
0s
tests : reduce FA test sizes (#28842)
python-type-check.yml #462 -Commit 4a89937354 pushed by vrr
upstream
2026-09-14 17:45:41 +00:00
0s
tests : reduce FA test sizes (#28842)
python-check-requirements.yml #461 -Commit 4a89937354 pushed by vrr
upstream
2026-09-15 01:34:22 +00:00
0s
Add IQ type handling for MoE (#28476)
python-type-check.yml #460 -Commit 304665fe7a pushed by vrr
upstream
2026-09-10 13:34:16 +00:00
0s
Revert "CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#24546)" (#28551)
python-type-check.yml #459 -Commit e71b80510c pushed by vrr
upstream
2026-09-08 19:34:15 +00:00
0s
Revert "CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#24546)" (#28551)
python-check-requirements.yml #458 -Commit e71b80510c pushed by vrr
upstream
2026-09-08 19:34:15 +00:00
0s
Revert "CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#24546)" (#28551)
pre-tokenizer-hashes.yml #457 -Commit e71b80510c pushed by vrr
upstream
2026-09-08 19:34:15 +00:00
0s
sycl : fix test-backend-ops CI break && restore Kronecker product FWHT support (#28016) (#28254)
python-type-check.yml #456 -Commit 4d9176092d pushed by vrr
upstream
2026-09-06 07:34:14 +00:00
0s
sycl : fix test-backend-ops CI break && restore Kronecker product FWHT support (#28016) (#28254)
python-check-requirements.yml #455 -Commit 4d9176092d pushed by vrr
upstream
2026-09-06 07:34:14 +00:00
0s
sycl : fix test-backend-ops CI break && restore Kronecker product FWHT support (#28016) (#28254)
pre-tokenizer-hashes.yml #454 -Commit 4d9176092d pushed by vrr
upstream
2026-09-06 07:34:14 +00:00
0s
ggml : don't crash when backend search path can't be read (#28271)
update-ops-docs.yml #453 -Commit 4cbe8b070b pushed by vrr
upstream
2026-09-05 19:34:28 +00:00
0s