chore: ⬆️ Update TheTom/llama-cpp-turboquant to c26cbdffcf6fc9b7430cd6b117757e9a3f70b7ea#10235
Open
localai-bot wants to merge 1 commit into
Open
chore: ⬆️ Update TheTom/llama-cpp-turboquant to c26cbdffcf6fc9b7430cd6b117757e9a3f70b7ea#10235localai-bot wants to merge 1 commit into
c26cbdffcf6fc9b7430cd6b117757e9a3f70b7ea#10235localai-bot wants to merge 1 commit into
Conversation
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
2 times, most recently
from
June 11, 2026 20:56
33783df to
95d0d4f
Compare
localai-bot
changed the title
73eb521daebc85da7c91d37178940b99a5524cf6f0d5cc9f71babf7cba8679a06efd602d26b70b06
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
2 times, most recently
from
June 13, 2026 20:34
7c48dfd to
2467c24
Compare
localai-bot
changed the title
f0d5cc9f71babf7cba8679a06efd602d26b70b067985f6b90bf19881ab7c7a8444954e91cae36056
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
4 times, most recently
from
June 17, 2026 20:50
ba90636 to
b2603de
Compare
localai-bot
changed the title
7985f6b90bf19881ab7c7a8444954e91cae3605635ac80d55b8e8e2a0d179413caddc2622b54c248
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
from
June 19, 2026 20:37
b2603de to
b863245
Compare
localai-bot
changed the title
35ac80d55b8e8e2a0d179413caddc2622b54c2484595fff0bbd15ee01663699b788eea70e7e1cd69
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
6 times, most recently
from
June 24, 2026 20:45
fe42778 to
beacee4
Compare
localai-bot
changed the title
4595fff0bbd15ee01663699b788eea70e7e1cd69a33ef00b13476e9c609caecc3c1c015b8615011d
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
2 times, most recently
from
June 26, 2026 21:24
a21dc73 to
2de5c5b
Compare
mudler
added a commit
to ci-forks/LocalAI
that referenced
this pull request
Jun 27, 2026
…10235) The fork a33ef00b HIP-ported ggml_cuda_copy2d_across_devices() itself (it now guards the cudaMemcpy3DPeer fast path with #if !defined(GGML_USE_HIP) && !defined(GGML_USE_MUSA) and falls back to a plain 2D device-to-device copy), so the former copy2d hunk's anchors went stale. Retire that hunk and re-anchor the still-needed event hunk: ggml_backend_cuda_device_event_new() still uses plain cudaEventCreate, which ggml's HIP shim does not alias, so keep the cudaEventCreateWithFlags (cudaEventDisableTiming) rewrite. Validated with apply-patches.sh against a fresh clone at the pinned commit. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code]
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
from
June 27, 2026 22:32
fd438a1 to
787c635
Compare
mudler
added a commit
to ci-forks/LocalAI
that referenced
this pull request
Jun 27, 2026
…10235) The fork a33ef00b HIP-ported ggml_cuda_copy2d_across_devices() itself (it now guards the cudaMemcpy3DPeer fast path with #if !defined(GGML_USE_HIP) && !defined(GGML_USE_MUSA) and falls back to a plain 2D device-to-device copy), so the former copy2d hunk's anchors went stale. Retire that hunk and re-anchor the still-needed event hunk: ggml_backend_cuda_device_event_new() still uses plain cudaEventCreate, which ggml's HIP shim does not alias, so keep the cudaEventCreateWithFlags (cudaEventDisableTiming) rewrite. Validated with apply-patches.sh against a fresh clone at the pinned commit. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code]
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
3 times, most recently
from
June 30, 2026 20:44
db5dabc to
b730ea9
Compare
localai-bot
changed the title
a33ef00b13476e9c609caecc3c1c015b8615011d0c8fcfe737ac7cfa79a5b8558024fd7ede79010f
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
from
July 1, 2026 20:40
b730ea9 to
7a1fcf7
Compare
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
3 times, most recently
from
July 6, 2026 21:34
2e78b9b to
88a3c62
Compare
localai-bot
changed the title
558c6b78e4f8cf92ec19539ff89b6d13f4183feb3d42fa1eb6e9f35c80ac86084637f574c3c764db
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
3 times, most recently
from
July 9, 2026 20:38
9777cc8 to
08694ce
Compare
localai-bot
changed the title
3d42fa1eb6e9f35c80ac86084637f574c3c764db206e18efc2966e8f0176e6f7012f8f9610195937
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
from
July 10, 2026 20:34
08694ce to
6f316dd
Compare
localai-bot
changed the title
206e18efc2966e8f0176e6f7012f8f9610195937c3e6dbb13d40e2e42f7a964bd5d745fbf86e4495
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
2 times, most recently
from
July 12, 2026 20:19
f4319bb to
8d7cfce
Compare
localai-bot
changed the title
c3e6dbb13d40e2e42f7a964bd5d745fbf86e44954503343ffc05c09f6b50c309c8ecbabb49c66ea2
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
2 times, most recently
from
July 14, 2026 21:10
92f2c17 to
2fd33b5
Compare
localai-bot
changed the title
4503343ffc05c09f6b50c309c8ecbabb49c66ea2f27268914e948aec208937e8b867a68d85f886ce
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
3 times, most recently
from
July 17, 2026 20:23
fa87b16 to
edf201b
Compare
Collaborator
|
The current red matrix is a real patch-refresh failure, not infra: upstream commit |
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
from
July 18, 2026 20:19
edf201b to
568cf0f
Compare
localai-bot
changed the title
f27268914e948aec208937e8b867a68d85f886ce471fb4ec8fc75bbebbcb81d4d6b5e260e9c6e831
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
from
July 19, 2026 20:20
568cf0f to
efc2404
Compare
localai-bot
changed the title
471fb4ec8fc75bbebbcb81d4d6b5e260e9c6e831c26cbdffcf6fc9b7430cd6b117757e9a3f70b7ea
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
2 times, most recently
from
July 22, 2026 01:09
965bd90 to
4b35fc2
Compare
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
localai-bot
force-pushed
the
update/TURBOQUANT_VERSION
branch
from
July 22, 2026 21:49
4b35fc2 to
7d6bfb4
Compare
Owner
|
@localai-org-maint-bot supersede this one in a new pr |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Changes: https://github.com/TheTom/llama-cpp-turboquant/compare/7d9715f1f071fa07c7b2ad3dbfd320b314139e65..c26cbdffcf6fc9b7430cd6b117757e9a3f70b7ea