[pull] main from abetlen:main by pull[bot] · Pull Request #3 · imotai/llama-cpp-python

pull · 2023-11-03T02:27:53Z

See Commits and Changes for more details.

Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

Bumps [pypa/cibuildwheel](https://github.com/pypa/cibuildwheel) from 2.19.1 to 2.19.2. - [Release notes](https://github.com/pypa/cibuildwheel/releases) - [Changelog](https://github.com/pypa/cibuildwheel/blob/main/docs/changelog.md) - [Commits](pypa/cibuildwheel@v2.19.1...v2.19.2) --- updated-dependencies: - dependency-name: pypa/cibuildwheel dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Andrei <abetlen@gmail.com>

Bumps [microsoft/setup-msbuild](https://github.com/microsoft/setup-msbuild) from 1.1 to 1.3. - [Release notes](https://github.com/microsoft/setup-msbuild/releases) - [Changelog](https://github.com/microsoft/setup-msbuild/blob/main/building-release.md) - [Commits](microsoft/setup-msbuild@v1.1...v1.3) --- updated-dependencies: - dependency-name: microsoft/setup-msbuild dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Andrei <abetlen@gmail.com>

* Update Dockerfile * Update Dockerfile * Update Dockerfile * Update Dockerfile * Update Dockerfile * Update Dockerfile * Update Dockerfile * Update build-docker.yaml * Update Dockerfile * Update Dockerfile * Remove docker login --------- Co-authored-by: Andrei Betlen <abetlen@gmail.com>

Co-authored-by: omer.yentur <omer.yentur@krontech.com> Co-authored-by: Andrei <abetlen@gmail.com>

Co-authored-by: Andrei <abetlen@gmail.com>

Missing ll

* reapply changes after sync with main branch * change repeat_penalty to 1.0 to match llama.cpp defaults --------- Co-authored-by: Andrei <abetlen@gmail.com>

Bumps [microsoft/setup-msbuild](https://github.com/microsoft/setup-msbuild) from 1.3 to 2. - [Release notes](https://github.com/microsoft/setup-msbuild/releases) - [Changelog](https://github.com/microsoft/setup-msbuild/blob/main/building-release.md) - [Commits](microsoft/setup-msbuild@v1.3...v2) --- updated-dependencies: - dependency-name: microsoft/setup-msbuild dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* ci: publish CPU wheels as py3-none * docs: add changelog entry for py3-none wheel tags

* refactor: replace deprecated llama.cpp references * docs: update changelog for recent llama.cpp changes

* feat: Update llama.cpp to ggml-org/llama.cpp@3bd9aa1f9 * docs: Update changelog for llama.cpp bump

* feat: Update llama.cpp to ggml-org/llama.cpp@f53577432 * docs: Update changelog for llama.cpp f53577432 * docs: Keep one unreleased llama.cpp changelog entry

* fix(ci): Build one arm64 py3 release wheel * docs: Update changelog for arm64 release wheel fix

* feat(ci): re-enable Windows CUDA wheel builds * fix(ci): use ninja for Windows CUDA wheels * fix(ci): normalize Windows CUDA CMake paths * feat(ci): add CUDA 12.5 wheel builds * fix(ci): avoid Windows CUDA 12.5 toolkit meta-package * fix(ci): include CUDA 12.5 Windows libraries * chore(ci): simplify Windows CUDA wheel workflow * docs: update changelog for Windows CUDA wheels

… in add_sequence (#2205) Fix batched embedding output flags for multi-sequence embed calls. Closes #2199.

* fix: configure n_seq_max for embeddings * refactor: keep embedding n_seq_max internal

…ng' INFO (#2208) (#2212)

…ch processing (#2217) * fix(embedding): set kv_unified=True when embedding=True to enable batch processing * chore: update changelog for batch embedding fix --------- Co-authored-by: abetlen <abetlen@gmail.com>

* feat: update llama.cpp to 91e84fed6 * chore: document mtmd_caps c declaration

Co-authored-by: abetlen <abetlen@gmail.com>

pull Bot added ⤵️ pull merge-conflict Resolve conflicts manually labels Nov 4, 2023

abetlen force-pushed the main branch 5 times, most recently from 4408d7a to cc0fe43 Compare November 14, 2023 20:30

abetlen force-pushed the main branch from 0188482 to c96b2da Compare April 17, 2024 14:06

abetlen force-pushed the main branch 2 times, most recently from 5a7ad37 to dc20e8c Compare July 2, 2024 05:39

abetlen and others added 20 commits July 9, 2024 00:29

fix: Update LLAMA_ flags to GGML_ flags

1a55417

fix(ci): Update LLAMA_ flags to GGML_

09a4f78

fix(docs): Update LLAMA_ flags to GGML_ flags

0481a3a

fix(docs): Remove kompute backend references

fccff80

fix(misc): Update LLAMA_ flags to GGML_

276ea28

chore: Bump version

aaf4cbe

fix(misc): Format

c1ae815

fix(minor): Minor ruff fixes

08f2bb3

feat(ci): Update simple Dockerfile (#1459)

f7f4fa8

Co-authored-by: omer.yentur <omer.yentur@krontech.com> Co-authored-by: Andrei <abetlen@gmail.com>

feat: Update llama.cpp

7613d23

fix(server): Use split_mode from model settings (#1594)

66d5cdd

Co-authored-by: Andrei <abetlen@gmail.com>

fix(docs): Update README.md typo (#1589)

797f54c

Missing ll

fix: Change repeat_penalty to 1.0 to match llama.cpp defaults (#1590)

0700476

* reapply changes after sync with main branch * change repeat_penalty to 1.0 to match llama.cpp defaults --------- Co-authored-by: Andrei <abetlen@gmail.com>

feat: Add 'required' literal to ChatCompletionToolChoiceOption (#1597)

3638f73

feat: Update llama.cpp

5105f40

chore: Bump version

816d491

abetlen and others added 30 commits March 29, 2026 00:31

ci: publish release wheels as py3-none (#2166)

7613aca

* ci: publish CPU wheels as py3-none * docs: add changelog entry for py3-none wheel tags

feat(server): add model-load chat_template_kwargs (#2168)

7257ba9

feat: Update llama.cpp to ggml-org/llama.cpp@f49e917 (#2169)

100b275

fix(misc): replace deprecated llama.cpp references (#2170)

08e088c

* refactor: replace deprecated llama.cpp references * docs: update changelog for recent llama.cpp changes

chore: bump version to 0.3.20 (#2171)

02d6bee

feat: Update llama.cpp to ggml-org/llama.cpp@3bd9aa1f9 (#2176)

1bcc5bc

* feat: Update llama.cpp to ggml-org/llama.cpp@3bd9aa1f9 * docs: Update changelog for llama.cpp bump

feat: Update llama.cpp to ggml-org/llama.cpp@227ed28e1 (#2182)

1b1a320

feat: Update llama.cpp to ggml-org/llama.cpp@f53577432 (#2189)

d87bf08

* feat: Update llama.cpp to ggml-org/llama.cpp@f53577432 * docs: Update changelog for llama.cpp f53577432 * docs: Keep one unreleased llama.cpp changelog entry

fix(ci): Build one arm64 py3 release wheel (#2191)

511b3f4

* fix(ci): Build one arm64 py3 release wheel * docs: Update changelog for arm64 release wheel fix

chore: bump version to 0.3.21 (#2192)

c8075d1

fix(ci): Repair py3 CPU release wheels (#2193)

195cc59

fix(ci): Scope CPU release wheel selectors by OS (#2194)

d2bcbac

fix(docs): update mkdocstrings inventories config (#2195)

c6dc905

feat: Update llama.cpp to ggml-org/llama.cpp@63d93d173 (#2197)

587d94a

chore: bump version to 0.3.22 (#2200)

9cf0ce7

fix(ci): pass CUDA unsupported compiler flag during detection (#2201)

2bfd80c

fix(ci): pass CUDA compiler arg for Windows detection (#2202)

04a3638

fix(ci): install CUDA CCCL headers for wheel builds (#2203)

bc6ff9f

fix(ci): skip unsupported Windows CUDA versions (#2204)

14d7846

fix(_internals): use n_tokens0 offset when enabling last-token logits…

90e8df9

… in add_sequence (#2205) Fix batched embedding output flags for multi-sequence embed calls. Closes #2199.

fix: configure n_seq_max for batched embeddings (#2206)

128c331

* fix: configure n_seq_max for embeddings * refactor: keep embedding n_seq_max internal

feat: update llama.cpp to 5d6f18a63 (#2207)

f774690

fix(embed): mark all tokens as output to suppress llama.cpp 'overridi…

f8c1f36

…ng' INFO (#2208) (#2212)

feat: update llama.cpp to 7d442abf (#2214)

5684112

chore: bump version to 0.3.23 (#2215)

4a1a8ec

fix(embedding): set kv_unified=True when embedding=True to enable bat…

95ccb19

…ch processing (#2217) * fix(embedding): set kv_unified=True when embedding=True to enable batch processing * chore: update changelog for batch embedding fix --------- Co-authored-by: abetlen <abetlen@gmail.com>

feat: Update llama.cpp to ggml-org/llama.cpp@91e84fed6 (#2218)

7664a3e

* feat: update llama.cpp to 91e84fed6 * chore: document mtmd_caps c declaration

chore: migrate llama.cpp submodule to ggml-org (#2034)

c7bea71

Co-authored-by: abetlen <abetlen@gmail.com>

feat: Update llama.cpp to b9a2170fc (#2223)

5dd9b1c

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[pull] main from abetlen:main#3

[pull] main from abetlen:main#3
pull[bot] wants to merge 934 commits into
imotai:mainfrom
abetlen:main

pull Bot commented Nov 3, 2023 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

20 participants

Conversation

pull Bot commented Nov 3, 2023 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

20 participants

pull Bot commented Nov 3, 2023 •

edited

Loading