[pull] main from abetlen:main#1

Open

pull[bot] wants to merge 1180 commits intoFreed-Wu:mainfrom

This pull request is big! We're only showing the most recent 250 commits

Commits on May 13, 2024

feat: Update llama.cpp
abetlen
committed
43ba152
Copy full SHA for 43ba152

Commits on May 14, 2024

Update llama.cpp
abetlen
committed
50f5c74
Copy full SHA for 50f5c74
chore(deps): bump pypa/cibuildwheel from 2.17.0 to 2.18.0 (#1453)
Show description for 4b54f79
dependabot[bot]
authored
4b54f79
Copy full SHA for 4b54f79
misc: Remove unnecessary metadata lookups (#1448)
Show description for 389e09c
CISC
authored
389e09c
Copy full SHA for 389e09c
feat: add MinTokensLogitProcessor and min_tokens argument to server (#1333)
Show description for 5212fb0
twaka
authored
5212fb0
Copy full SHA for 5212fb0

Commits on May 16, 2024

feat: Update llama.cpp
abetlen
committed
ca8e3c9
Copy full SHA for ca8e3c9
Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main
abetlen
committed
e811a81
Copy full SHA for e811a81
fix: segfault for models without eos / bos tokens. Closes #1463
abetlen
committed
d99a6ba
Copy full SHA for d99a6ba
chore: Bump version
abetlen
committed
b564d05
Copy full SHA for b564d05

Commits on May 17, 2024

example: LLM inference with Ray Serve (#1465)
rgerganov
authored
03f171e
Copy full SHA for 03f171e

Commits on May 18, 2024

feat: Update llama.cpp
abetlen
committed
d8a3b01
Copy full SHA for d8a3b01
Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main
abetlen
committed
3dbfec7
Copy full SHA for 3dbfec7

Commits on May 22, 2024

feat: Update llama.cpp
abetlen
committed
5a595f0
Copy full SHA for 5a595f0

Commits on May 24, 2024

feat: Update llama.cpp
abetlen
committed
087cc0b
Copy full SHA for 087cc0b
feat: Improve Llama.eval performance by avoiding list conversion (#1476)
Show description for 5cae104

thoughtp0lice
and
abetlen
authored
5cae104
Copy full SHA for 5cae104
chore: Bump version
abetlen
committed
a4c9ab8
Copy full SHA for a4c9ab8
docs: Update multi-modal model section
abetlen
committed
ec43e89
Copy full SHA for ec43e89
fix(docs): Fix link typo
abetlen
committed
9e8d7d5
Copy full SHA for 9e8d7d5
docs: Fix table formatting
abetlen
committed
2d89964
Copy full SHA for 2d89964

Commits on May 27, 2024

feat: Update llama.cpp
abetlen
committed
454c9bb
Copy full SHA for 454c9bb
chore(deps): bump pypa/cibuildwheel from 2.18.0 to 2.18.1 (#1472)
Show description for c564007

dependabot[bot]
and
abetlen
authored
c564007
Copy full SHA for c564007

Commits on May 29, 2024

feat: Update llama.cpp
abetlen
committed
c26004b
Copy full SHA for c26004b
misc: Update debug build to keep all debug symbols for easier gdb debugging
abetlen
committed
2907c26
Copy full SHA for 2907c26
Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main
abetlen
committed
10b7c50
Copy full SHA for 10b7c50
fix: fix string value kv_overrides. Closes #1487
abetlen
committed
df45a4b
Copy full SHA for df45a4b
fix: adjust kv_override member names to match llama.cpp
abetlen
committed
91d05ab
Copy full SHA for 91d05ab
fix: Fix typo in Llama3VisionAlphaChatHandler. Closes #1488
abetlen
committed
165b4dc
Copy full SHA for 165b4dc

Commits on Jun 1, 2024

fix: Use numpy recarray for candidates data, fixes bug with temp < 0
abetlen
committed
af3ed50
Copy full SHA for af3ed50
Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main
abetlen
committed
a6457ba
Copy full SHA for a6457ba

Commits on Jun 3, 2024

misc: Improve llava error messages
abetlen
committed
6b018e0
Copy full SHA for 6b018e0

Commits on Jun 4, 2024

feat: Update llama.cpp
abetlen
committed
cd3f1bb
Copy full SHA for cd3f1bb
fix: Disable Windows+CUDA workaround when compiling for HIPBLAS (#1493)
Show description for ae5682f

Engininja2
and
abetlen
authored
ae5682f
Copy full SHA for ae5682f
chore: Bump version
abetlen
committed
c3ef41b
Copy full SHA for c3ef41b
Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main
abetlen
committed
951e39c
Copy full SHA for 951e39c
fix: Avoid duplicate special tokens in chat formats (#1439)
Show description for 027f7bc

CISC
and
abetlen
authored
027f7bc
Copy full SHA for 027f7bc
fix: fix logprobs when BOS is not present (#1471)
Show description for 6e0642c
a-ghorbani
authored
6e0642c
Copy full SHA for 6e0642c
feat: adding `rpc_servers` parameter to `Llama` class (#1477)
Show description for d634efc

chraac
and
abetlen
authored
d634efc
Copy full SHA for d634efc

Commits on Jun 7, 2024

feat: Update llama.cpp
abetlen
committed
255e1b4
Copy full SHA for 255e1b4

Commits on Jun 9, 2024

feat: Update llama.cpp
abetlen
committed
83d6b26
Copy full SHA for 83d6b26

Commits on Jun 10, 2024

feat: Update llama.cpp
abetlen
committed
1615eb9
Copy full SHA for 1615eb9
chore: Bump version
abetlen
committed
86a38ad
Copy full SHA for 86a38ad

Commits on Jun 13, 2024

feat: Update llama.cpp
abetlen
committed
e342161
Copy full SHA for e342161
feat: Support SPM infill (#1492)
Show description for dbcf64c

CISC
and
abetlen
authored
dbcf64c
Copy full SHA for dbcf64c
feat: Add `.close()` method to `Llama` class to explicitly free model from memory (#1513)
Show description for 320a5d7

jkawamoto
and
abetlen
authored
320a5d7
Copy full SHA for 320a5d7
chore(deps): bump pypa/cibuildwheel from 2.18.1 to 2.19.0 (#1522)
Show description for 5af8163
dependabot[bot]
authored
5af8163
Copy full SHA for 5af8163
feat: Update workflows and pre-built wheels (#1416)
Show description for 9e396b3

Smartappli
and
abetlen
authored
9e396b3
Copy full SHA for 9e396b3
feat: Update llama.cpp
abetlen
committed
8401c6f
Copy full SHA for 8401c6f

Commits on Jun 17, 2024

feat: Update llama.cpp
abetlen
committed
f4491c4
Copy full SHA for f4491c4

Commits on Jun 19, 2024

fix: Make destructor to automatically call .close() method on Llama class.
abetlen
committed
4c1d74c
Copy full SHA for 4c1d74c
feat: Update llama.cpp
abetlen
committed
554fd08
Copy full SHA for 554fd08
chore: Bump version
abetlen
committed
6c33190
Copy full SHA for 6c33190

Commits on Jun 20, 2024

docs: Remove references to deprecated opencl backend. Closes #1512
abetlen
committed
d98a24a
Copy full SHA for d98a24a

Commits on Jun 21, 2024

feat: Update llama.cpp
abetlen
committed
5beec1a
Copy full SHA for 5beec1a
docs: Update readme examples to use newer Qwen2 model (#1544)
jncraton
authored
27d5358
Copy full SHA for 27d5358
chore(deps): bump docker/build-push-action from 5 to 6 (#1539)
Show description for 398fe81
dependabot[bot]
authored
398fe81
Copy full SHA for 398fe81
chore(deps): bump pypa/cibuildwheel from 2.18.1 to 2.19.1 (#1527)
Show description for 35c980e
dependabot[bot]
authored
35c980e
Copy full SHA for 35c980e
feat: Update llama_cpp.py bindings
abetlen
committed
04959f1
Copy full SHA for 04959f1

Commits on Jul 2, 2024

feat: Update llama.cpp
abetlen
committed
117cbb2
Copy full SHA for 117cbb2
fix(server): Update `embeddings=False` by default. Embeddings should be enabled by default for embedding models.
abetlen
committed
bf5e0bb
Copy full SHA for bf5e0bb
fix(ci): Fix the CUDA workflow (#1551)
oobabooga
authored
73ddf29
Copy full SHA for 73ddf29
misc: Install shared libraries to lib subdirectory
abetlen
committed
c546c94
Copy full SHA for c546c94
Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main
abetlen
committed
92bad6e
Copy full SHA for 92bad6e
fix: Update shared library rpath
abetlen
committed
139774b
Copy full SHA for 139774b
fix: force $ORIGIN rpath for shared library files
abetlen
committed
d5f6a15
Copy full SHA for d5f6a15
fix: Fix installation location for shared libraries
abetlen
committed
e51f200
Copy full SHA for e51f200
fix: Fix RPATH so it works on macos
abetlen
committed
73fe013
Copy full SHA for 73fe013
fix: Copy dependencies for windows
Show description for dc20e8c
abetlen
committed
dc20e8c
Copy full SHA for dc20e8c
fix(server): Fix bug in FastAPI streaming response where dependency was released before request completes causing SEGFAULT
abetlen
committed
296304b
Copy full SHA for 296304b
feat: Update llama.cpp
abetlen
committed
bd5d17b
Copy full SHA for bd5d17b
chore: Bump version
abetlen
committed
b4cc923
Copy full SHA for b4cc923
fix(ci): Use LLAMA_CUDA for cuda wheels
abetlen
committed
4fb6fc1
Copy full SHA for 4fb6fc1
fix(misc): Fix type errors
abetlen
committed
387d01d
Copy full SHA for 387d01d
feat: Update llama.cpp
abetlen
committed
8992a1a
Copy full SHA for 8992a1a
fix(ci): Update macos image (macos-11 is removed)
abetlen
committed
3a551eb
Copy full SHA for 3a551eb
chore: Bump version
abetlen
committed
01bddd6
Copy full SHA for 01bddd6

Commits on Jul 4, 2024

feat: Update llama.cpp
abetlen
committed
7e20e34
Copy full SHA for 7e20e34

Commits on Jul 6, 2024

feat: Update llama.cpp
abetlen
committed
62804ee
Copy full SHA for 62804ee
fix: update token_to_piece
abetlen
committed
157d913
Copy full SHA for 157d913

Commits on Jul 9, 2024

feat: Update llama.cpp
abetlen
committed
218d361
Copy full SHA for 218d361
fix: Update LLAMA_ flags to GGML_ flags
abetlen
committed
1a55417
Copy full SHA for 1a55417
fix(ci): Update LLAMA_ flags to GGML_
abetlen
committed
09a4f78
Copy full SHA for 09a4f78
fix(docs): Update LLAMA_ flags to GGML_ flags
abetlen
committed
0481a3a
Copy full SHA for 0481a3a
fix(docs): Remove kompute backend references
abetlen
committed
fccff80
Copy full SHA for fccff80
fix(misc): Update LLAMA_ flags to GGML_
abetlen
committed
276ea28
Copy full SHA for 276ea28
chore: Bump version
abetlen
committed
aaf4cbe
Copy full SHA for aaf4cbe
chore(deps): bump pypa/cibuildwheel from 2.19.1 to 2.19.2 (#1568)
Show description for 14760c6

dependabot[bot]
and
abetlen
authored
14760c6
Copy full SHA for 14760c6
chore(deps): bump microsoft/setup-msbuild from 1.1 to 1.3 (#1569)
Show description for e31f096

dependabot[bot]
and
abetlen
authored
e31f096
Copy full SHA for e31f096
feat(ci): Dockerfile update base images and post-install cleanup (#1530)
Show description for b77e507

Smartappli
and
abetlen
authored
b77e507
Copy full SHA for b77e507
fix(misc): Format
abetlen
committed
c1ae815
Copy full SHA for c1ae815
fix(minor): Minor ruff fixes
abetlen
committed
08f2bb3
Copy full SHA for 08f2bb3
feat(ci): Update simple Dockerfile (#1459)
Show description for f7f4fa8

authored
f7f4fa8
Copy full SHA for f7f4fa8

Commits on Jul 17, 2024

feat: Update llama.cpp
abetlen
committed
7613d23
Copy full SHA for 7613d23
fix(server): Use split_mode from model settings (#1594)
Show description for 66d5cdd

grider-withourai
and
abetlen
authored
66d5cdd
Copy full SHA for 66d5cdd
fix(docs): Update README.md typo (#1589)
Show description for 797f54c
ericcurtin
authored
797f54c
Copy full SHA for 797f54c

Commits on Jul 18, 2024

fix: Change repeat_penalty to 1.0 to match llama.cpp defaults (#1590)
Show description for 0700476

ddh0
and
abetlen
authored
0700476
Copy full SHA for 0700476
feat: Add 'required' literal to ChatCompletionToolChoiceOption (#1597)
mjschock
authored
3638f73
Copy full SHA for 3638f73

Commits on Jul 20, 2024

chore(deps): bump microsoft/setup-msbuild from 1.3 to 2 (#1585)
Show description for f95057a
dependabot[bot]
authored
f95057a
Copy full SHA for f95057a

Commits on Jul 22, 2024

feat: Update llama.cpp
abetlen
committed
5105f40
Copy full SHA for 5105f40
chore: Bump version
abetlen
committed
816d491
Copy full SHA for 816d491

Commits on Jul 24, 2024

feat: Update llama.cpp
abetlen
committed
a14b49d
Copy full SHA for a14b49d

Commits on Jul 28, 2024

feat: Update llama.cpp
abetlen
committed
dccb148
Copy full SHA for dccb148
fix: Correcting run.sh filepath in Simple Docker implementation (#1626)
mashuk999
authored
9ed6b27
Copy full SHA for 9ed6b27
chore: Bump version
abetlen
committed
4bf3b43
Copy full SHA for 4bf3b43

Commits on Jul 31, 2024

feat: Update llama.cpp
abetlen
committed
cffb4ec
Copy full SHA for cffb4ec
feat: Update llama.cpp
abetlen
committed
53c6f32
Copy full SHA for 53c6f32
feat: FreeBSD compatibility (#1635)
yurivict
authored
0b1a8d8
Copy full SHA for 0b1a8d8
fix(docker): Update Dockerfile build options from `LLAMA_` to `GGML_` (#1634)
Smartappli
authored
8297a0d
Copy full SHA for 8297a0d
fix(docker): Fix GGML_CUDA param (#1633)
Smartappli
authored
ac02174
Copy full SHA for ac02174
fix(docker): Update Dockerfile BLAS options (#1632)
Smartappli
authored
8a12c9f
Copy full SHA for 8a12c9f
fix : Missing LoRA adapter after API change (#1630)
shamitv
authored
1f0b9a2
Copy full SHA for 1f0b9a2
chore: Bump version
abetlen
committed
f7b9e6d
Copy full SHA for f7b9e6d

Commits on Aug 4, 2024

fix: llama_grammar_accept_token arg order (#1649)
Show description for 5575fed
tc-wolf
authored
5575fed
Copy full SHA for 5575fed

Commits on Aug 7, 2024

feat: Ported back new grammar changes from C++ to Python implementation (#1637)
Show description for dff186c

ExtReMLapin
and
abetlen
authored
dff186c
Copy full SHA for dff186c
feat: Update llama.cpp
abetlen
committed
18f58fe
Copy full SHA for 18f58fe
chore: Bump version
abetlen
committed
ce6466f
Copy full SHA for ce6466f
feat(ci): Re-build wheel index automatically when releases are created
abetlen
committed
198f47d
Copy full SHA for 198f47d
feat: Update llama.cpp
abetlen
committed
a07b337
Copy full SHA for a07b337
fix: Include all llama.cpp source files and subdirectories
abetlen
committed
9cad571
Copy full SHA for 9cad571
chore: Bump version
abetlen
committed
8432116
Copy full SHA for 8432116
feat: Add more detailed log for prefix-match (#1659)
Show description for e966f3b

xu-song
and
abetlen
authored
e966f3b
Copy full SHA for e966f3b
chore(deps): bump pypa/cibuildwheel from 2.19.2 to 2.20.0 (#1657)
Show description for 131db40
dependabot[bot]
authored
131db40
Copy full SHA for 131db40
feat: Enable recursive search of HFFS.ls when using `from_pretrained` (#1656)
Show description for 5e39a85

benHeid
and
abetlen
authored
5e39a85
Copy full SHA for 5e39a85

Commits on Aug 8, 2024

feat: Update llama.cpp
abetlen
committed
c5de5d3
Copy full SHA for c5de5d3
Merge branch 'main' of github.com:abetlen/llama-cpp-python into main
abetlen
committed
bfb42b7
Copy full SHA for bfb42b7
fix: grammar prints on each call. Closes #1666
abetlen
committed
0998ea0
Copy full SHA for 0998ea0
fix: typo
abetlen
committed
7aaf701
Copy full SHA for 7aaf701

Commits on Aug 10, 2024

feat: Update llama.cpp
abetlen
committed
45de9d5
Copy full SHA for 45de9d5

Commits on Aug 12, 2024

feat: Update llama.cpp
abetlen
committed
4244151
Copy full SHA for 4244151
fix: Added back from_file method to LlamaGrammar (#1673)
ExtReMLapin
authored
95a1533
Copy full SHA for 95a1533
fix: only print 'cache saved' in verbose mode (#1668)
Show description for 9bab46f

lsorber
and
abetlen
authored
9bab46f
Copy full SHA for 9bab46f
feat: Update llama.cpp
abetlen
committed
8ed663b
Copy full SHA for 8ed663b

Commits on Aug 13, 2024

chore: Bump version
abetlen
committed
fc19cc7
Copy full SHA for fc19cc7

Commits on Aug 15, 2024

feat: Update llama.cpp
abetlen
committed
63d65ac
Copy full SHA for 63d65ac
fix: missing dependencies for test (#1680)
jkawamoto
authored
78e35c4
Copy full SHA for 78e35c4
fix: Llama.close didn't free lora adapter (#1679)
jkawamoto
authored
3c7501b
Copy full SHA for 3c7501b

Commits on Aug 16, 2024

feat: Update llama.cpp
abetlen
committed
7bf07ec
Copy full SHA for 7bf07ec
Merge branch 'main' of github.com:abetlen/llama-cpp-python into main
abetlen
committed
658b244
Copy full SHA for 658b244

Commits on Aug 19, 2024

feat: Update llama.cpp
abetlen
committed
a2ba731
Copy full SHA for a2ba731
chore: Bump version
abetlen
committed
d7328ef
Copy full SHA for d7328ef

Commits on Aug 21, 2024

feat: Update llama.cpp
abetlen
committed
a20f13f
Copy full SHA for a20f13f

Commits on Aug 22, 2024

feat: Update llama.cpp
abetlen
committed
259ee15
Copy full SHA for 259ee15

Commits on Aug 28, 2024

feat: Update llama.cpp
abetlen
committed
82ae7f9
Copy full SHA for 82ae7f9

Commits on Aug 29, 2024

feat: Add MiniCPMv26 chat handler.
abetlen
committed
f70df82
Copy full SHA for f70df82
fix: Update name to MiniCPMv26ChatHandler
abetlen
committed
e251a0b
Copy full SHA for e251a0b
fix: pull all gh releases for self-hosted python index
abetlen
committed
c68e7fb
Copy full SHA for c68e7fb
feat: Add server chat_format minicpm-v-2.6 for MiniCPMv26ChatHandler
abetlen
committed
97d527e
Copy full SHA for 97d527e
docs: Add project icon courtesy of 🤗
abetlen
committed
b570fd3
Copy full SHA for b570fd3
docs: center icon and resize
abetlen
committed
cbbfad4
Copy full SHA for cbbfad4
docs: Add MiniCPM-V-2.6 to multi-modal model list
abetlen
committed
ad2deaf
Copy full SHA for ad2deaf
feat: Update llama.cpp
abetlen
committed
332720d
Copy full SHA for 332720d
chore: Bump version
abetlen
committed
077ecb6
Copy full SHA for 077ecb6
misc(fix): Update CHANGELOG
abetlen
committed
45001ac
Copy full SHA for 45001ac
docs: Update README
abetlen
committed
4b1e364
Copy full SHA for 4b1e364
docs: Update README
abetlen
committed
8b853c0
Copy full SHA for 8b853c0
docs: Update README
abetlen
committed
9cba3b8
Copy full SHA for 9cba3b8
feat: Enable detokenizing special tokens with `special=True` (#1596)
Show description for d981d32

benniekiss
and
abetlen
authored
d981d32
Copy full SHA for d981d32

Commits on Aug 30, 2024

fix: Use system message in og qwen format. Closes #1697
abetlen
committed
98eb092
Copy full SHA for 98eb092
feat: Update llama.cpp
abetlen
committed
dcb0d0c
Copy full SHA for dcb0d0c

Commits on Aug 31, 2024

feat: Update llama.cpp
abetlen
committed
9769e57
Copy full SHA for 9769e57

Commits on Sep 2, 2024

feat: Update llama.cpp
abetlen
committed
c3fc80a
Copy full SHA for c3fc80a

Commits on Sep 5, 2024

feat: Update llama.cpp
abetlen
committed
9497bcd
Copy full SHA for 9497bcd

Commits on Sep 6, 2024

feat: Update llama.cpp
abetlen
committed
c032fc6
Copy full SHA for c032fc6

Commits on Sep 18, 2024

feat(ci): Speed up CI workflows using `uv`, add support for CUDA 12.5 wheels
Show description for e529940

Smartappli
and
abetlen
authored
e529940
Copy full SHA for e529940
chore(deps): bump pypa/cibuildwheel from 2.20.0 to 2.21.1 (#1743)
Show description for a4e1451

dependabot[bot]
and
abetlen
authored
a4e1451
Copy full SHA for a4e1451

Commits on Sep 19, 2024

feat: Update sampling API for llama.cpp (#1742)
Show description for f8fcb3e
abetlen
authored
f8fcb3e
Copy full SHA for f8fcb3e
feat: Update llama.cpp
abetlen
committed
1e64664
Copy full SHA for 1e64664
misc: Format
abetlen
committed
9b64bb5
Copy full SHA for 9b64bb5
fix: Fix memory allocation of ndarray (#1704)
Show description for 22cedad

xu-song
and
abetlen
authored
22cedad
Copy full SHA for 22cedad
fix: Don't store scores internally unless logits_all=True. Reduces memory requirements for large context. Closes #1542
abetlen
committed
29afcfd
Copy full SHA for 29afcfd
feat: Add loading sharded GGUF files from HuggingFace with Llama.from_pretrained(additional_files=[...]) . Closes #1341
Show description for 84c0920

Gnurro
and
abetlen
authored
84c0920
Copy full SHA for 84c0920

Commits on Sep 20, 2024

feat: Update llama.cpp
abetlen
committed
47d7a62
Copy full SHA for 47d7a62
feat: Add option to configure n_ubatch
abetlen
committed
6c44a3f
Copy full SHA for 6c44a3f
docs: Add cuda 12.5 to README.md (#1750)
Show description for 49b1e73

Smartappli
and
abetlen
authored
49b1e73
Copy full SHA for 49b1e73
chore(deps): bump actions/cache from 3 to 4 (#1751)
Show description for 1324c0c

dependabot[bot]
and
abetlen
authored
1324c0c
Copy full SHA for 1324c0c

Commits on Sep 22, 2024

feat: Update llama.cpp
abetlen
committed
4744551
Copy full SHA for 4744551

Commits on Sep 25, 2024

feat: Update llama.cpp
abetlen
committed
926b414
Copy full SHA for 926b414
chore: Bump version
abetlen
committed
b3dfb42
Copy full SHA for b3dfb42
fix: install build dependency
abetlen
committed
8e07db0
Copy full SHA for 8e07db0
fix: install build dependency
abetlen
committed
65222bc
Copy full SHA for 65222bc

Commits on Sep 26, 2024

fix: Fix speculative decoding
abetlen
committed
9992c50
Copy full SHA for 9992c50
misc: Rename all_text to remaining_text (#1658)
Show description for 11d9562

xu-song
and
abetlen
authored
11d9562
Copy full SHA for 11d9562
fix: Additional fixes for speculative decoding
abetlen
committed
e975dab
Copy full SHA for e975dab
feat: Update llama.cpp
abetlen
committed
dca0c9a
Copy full SHA for dca0c9a
feat: Expose libggml in internal APIs (#1761)
Show description for 01c7607
abetlen
authored
01c7607
Copy full SHA for 01c7607

Commits on Sep 29, 2024

feat: Update llama.cpp
abetlen
committed
57e70bb
Copy full SHA for 57e70bb
chore: Bump version
abetlen
committed
7c4aead
Copy full SHA for 7c4aead

Commits on Oct 22, 2024

feat: Update llama.cpp
abetlen
committed
7403e00
Copy full SHA for 7403e00

Commits on Oct 31, 2024

feat: Update llama.cpp
abetlen
committed
e712cff
Copy full SHA for e712cff

Commits on Nov 15, 2024

feat: Update llama.cpp
abetlen
committed
cafa33e
Copy full SHA for cafa33e

Commits on Nov 16, 2024

Add missing ggml dependency
abetlen
committed
d1cb50b
Copy full SHA for d1cb50b
Add all missing ggml dependencies
abetlen
committed
2796f4e
Copy full SHA for 2796f4e
chore: Bump version
abetlen
committed
7ecdd94
Copy full SHA for 7ecdd94

Commits on Nov 28, 2024

feat: Update llama.cpp
abetlen
committed
f3fb90b
Copy full SHA for f3fb90b

Commits on Dec 6, 2024

feat: Update llama.cpp
abetlen
committed
7ba257e
Copy full SHA for 7ba257e
fix(ci): Explicitly install arm64 python version
abetlen
committed
9d06e36
Copy full SHA for 9d06e36
fix(ci): Explicitly set cmake osx architecture
abetlen
committed
fb0b8fe
Copy full SHA for fb0b8fe
fix(ci): Explicitly test on arm64 macos runner
abetlen
committed
72ed7b8
Copy full SHA for 72ed7b8
fix(ci): Use macos-14 runner
abetlen
committed
8988aaf
Copy full SHA for 8988aaf
fix(ci): Use macos-13 runner
abetlen
committed
f11a781
Copy full SHA for f11a781
fix(ci): Debug print python system architecture
abetlen
committed
9a09fc7
Copy full SHA for 9a09fc7
fix(ci): Update config
abetlen
committed
a412ba5
Copy full SHA for a412ba5
fix(ci): Install with regular pip
abetlen
committed
df05096
Copy full SHA for df05096
fix(ci): gg
abetlen
committed
1cd3f2c
Copy full SHA for 1cd3f2c
fix(ci): Use python3
abetlen
committed
b34f200
Copy full SHA for b34f200
fix(ci): Use default architecture chosen by action
abetlen
committed
d8cc231
Copy full SHA for d8cc231
fix(ci): Update CMakeLists.txt for macos
abetlen
committed
d5d5099
Copy full SHA for d5d5099
fix(ci): Remove cuda version 12.5.0 incompatibility with VS (#1838)
Show description for 4f17ae5

pabl-o-ce
and
abetlen
authored
4f17ae5
Copy full SHA for 4f17ae5
fix(ci): Remove CUDA 12.5 from index
abetlen
committed
991d9cd
Copy full SHA for 991d9cd
chore(deps): bump pypa/cibuildwheel from 2.21.1 to 2.22.0 (#1844)
Show description for 2795303
dependabot[bot]
authored
2795303
Copy full SHA for 2795303
fix: Fix pickling of Llama class by setting seed from _seed member. Closes #1769
abetlen
committed
2523472
Copy full SHA for 2523472
Merge branch 'main' of github.com:abetlen/llama-cpp-python into main
abetlen
committed
d553a54
Copy full SHA for d553a54
chore(deps): bump conda-incubator/setup-miniconda from 3.0.4 to 3.1.0 (#1821)
Show description for ddac04c
dependabot[bot]
authored
ddac04c
Copy full SHA for ddac04c
fix logit-bias type hint (#1802)
Show description for fa04cdc
ddh0
authored
fa04cdc
Copy full SHA for fa04cdc
docs: Remove ref to llama_eval in llama_cpp.py docs (#1819)
Show description for 38fbd29
richdougherty
authored
38fbd29
Copy full SHA for 38fbd29
fix: make content not required in ChatCompletionRequestAssistantMessage (#1807)
feloy
authored
4192210
Copy full SHA for 4192210
fix: Re-add suport for CUDA 12.5, add CUDA 12.6 (#1775)
Show description for 77a12a3

Smartappli
and
abetlen
authored
77a12a3
Copy full SHA for 77a12a3
fix: added missing exit_stack.close() to /v1/chat/completions (#1796)
Show description for 073b7e4
Ian321
authored
073b7e4
Copy full SHA for 073b7e4
fix: Avoid thread starvation on many concurrent requests by making use of asyncio to lock llama_proxy context (#1798)
Show description for 9bd0c95

gjpower
and
abetlen
authored
9bd0c95
Copy full SHA for 9bd0c95
fix(docs): Update development instructions (#1833)
Florents-Tselai
authored
1ea6154
Copy full SHA for 1ea6154
fix(examples): Refactor Batching notebook to use new sampler chain API (#1793)
Show description for d610477
lukestanley
authored
d610477
Copy full SHA for d610477
fix: chat API logprobs format (#1788)
Show description for 4f0ec65
domdomegg
authored
4f0ec65
Copy full SHA for 4f0ec65
misc: Update development Makefile
abetlen
committed
df136cb
Copy full SHA for df136cb
Merge branch 'main' of github.com:abetlen/llama-cpp-python into main
abetlen
committed
6889429
Copy full SHA for 6889429
misc: Update run server command
abetlen
committed
b9b50e5
Copy full SHA for b9b50e5

Commits on Dec 9, 2024

feat: Update llama.cpp
abetlen
committed
5585f8a
Copy full SHA for 5585f8a
Add CUDA 12.5 and 12.6 to generated output wheels
abetlen
committed
61508c2
Copy full SHA for 61508c2
chore: Bump version
abetlen
committed
a9fe0f8
Copy full SHA for a9fe0f8
fix(ci): hotfix for wheels
abetlen
committed
ca80802
Copy full SHA for ca80802
chore: Bump version
abetlen
committed
002f583
Copy full SHA for 002f583
fix(ci): update macos runner image to non-deprecated version
abetlen
committed
ea4d86a
Copy full SHA for ea4d86a
fix: add missing await statements for async exit_stack handling (#1858)
gjpower
authored
afedfc8
Copy full SHA for afedfc8
feat: Update llama.cpp
abetlen
committed
801a73a
Copy full SHA for 801a73a
chore: Bump version
abetlen
committed
803924b
Copy full SHA for 803924b

Commits on Dec 19, 2024

feat: Update llama.cpp
abetlen
committed
2bc1d97
Copy full SHA for 2bc1d97

Commits on Dec 30, 2024

feat: Update llama.cpp
abetlen
committed
c9dfad4
Copy full SHA for c9dfad4

Commits on Jan 8, 2025

feat: Update llama.cpp
abetlen
committed
1d5f534
Copy full SHA for 1d5f534
fix: streaming resource lock (#1879)
Show description for e8f14ce

gjpower
and
abetlen
authored
e8f14ce
Copy full SHA for e8f14ce
chore: Bump version
abetlen
committed
0580cf2
Copy full SHA for 0580cf2

Commits on Jan 29, 2025

feat: Update llama.cpp
abetlen
committed
80be68a
Copy full SHA for 80be68a
feat: Update llama.cpp
abetlen
committed
0b89fe4
Copy full SHA for 0b89fe4
fix(ci): Fix the CUDA workflow (#1894)
oobabooga
authored
14879c7
Copy full SHA for 14879c7
fix: error showing time spent in llama perf context print (#1898)
Show description for 4442ff8

shakalaca
and
abetlen
authored
4442ff8
Copy full SHA for 4442ff8
chore: Bump version
abetlen
committed
710e19a
Copy full SHA for 710e19a

Commits on Mar 12, 2025

feat: Update llama.cpp
abetlen
committed
344c106
Copy full SHA for 344c106
feat: Update llama.cpp
abetlen
committed
e232fae
Copy full SHA for e232fae
chore: Bump version
abetlen
committed
37eb5f0
Copy full SHA for 37eb5f0

Commits on Apr 11, 2025

feat: Update llama.cpp
abetlen
committed
99f2ebf
Copy full SHA for 99f2ebf

Commits on May 8, 2025

feat: Update llama.cpp
abetlen
committed
4c6514d
Copy full SHA for 4c6514d
chore: Bump version
abetlen
committed
cb2edb9
Copy full SHA for cb2edb9
hotfix: Disable curl support
abetlen
committed
b1d23df
Copy full SHA for b1d23df