containers/ramalama
1
0
Fork 0
mirror of https://github.com/containers/ramalama.git synced 2026-02-05 06:46:39 +01:00
Code Issues Wiki Activity
3,732 Commits 117 Branches 58 Tags
9b3155db60cc250dcc37ebdac68a237a99982ee7
Commit Graph

3732 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Mike Bonnet
9b3155db60 docs: fix docsite build by escaping angle bracket and curly brackets 
Required for successful mdx processing.

Signed-off-by: Mike Bonnet <mikeb@redhat.com>
 2026-01-27 10:13:01 -08:00
Mike Bonnet
b16ff0983d Merge pull request #2344 from mikebonnet/llama-build-less 
update llama.cpp build flags
 2026-01-27 08:30:02 -08:00
Mike Bonnet
77661ff982 Merge pull request #2348 from containers/renovate/registry.access.redhat.com-ubi9-ubi-9.x 
Update registry.access.redhat.com/ubi9/ubi Docker tag to v9.7-1769057030
 2026-01-27 08:26:17 -08:00
Mike Bonnet
bd3d7b9712 Merge pull request #2350 from containers/konflux/mintmaker/main/react-monorepo 
Update react monorepo to v19.2.4
 2026-01-27 08:24:24 -08:00
Mike Bonnet
bd6829b07e Merge pull request #2347 from containers/renovate/step-security-harden-runner-2.x 
[skip-ci] Update step-security/harden-runner action to v2.14.1
 2026-01-27 08:23:35 -08:00
Mike Bonnet
03ac1f44bf Merge pull request #2346 from containers/konflux/mintmaker/main/docsite-lockfile-maintenance 
Lock file maintenance
 2026-01-27 08:21:59 -08:00
Mike Bonnet
41d8acd485 Merge pull request #2321 from containers/konflux/references/main 
chore(deps): update konflux references
 2026-01-27 08:20:55 -08:00
red-hat-konflux-kflux-prd-rh03[bot]
643c148e58 Update react monorepo to v19.2.4 
Signed-off-by: red-hat-konflux-kflux-prd-rh03 <206760901+red-hat-konflux-kflux-prd-rh03[bot]@users.noreply.github.com>
 2026-01-27 00:47:18 +00:00
Mike Bonnet
face0f30fa Merge pull request #2340 from mikebonnet/disable-entrypoint-images 
stop building and releasing the entrypoint images
 2026-01-26 13:00:38 -08:00
renovate[bot]
e4534d5c33 Update registry.access.redhat.com/ubi9/ubi Docker tag to v9.7-1769057030 
Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
 2026-01-26 08:41:20 +00:00
renovate[bot]
38e905cb31 [skip-ci] Update step-security/harden-runner action to v2.14.1 
Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
 2026-01-26 05:26:08 +00:00
red-hat-konflux-kflux-prd-rh03[bot]
d96d015165 Lock file maintenance 
Signed-off-by: red-hat-konflux-kflux-prd-rh03 <206760901+red-hat-konflux-kflux-prd-rh03[bot]@users.noreply.github.com>
 2026-01-26 00:57:01 +00:00
Ian Eaves
739563aa77 Merge pull request #2339 from ramalama-labs/metrics 
Add benchmark metrics persistence
 2026-01-25 02:24:52 -06:00
Ian Eaves
82843f94f0 trial fix for bats-nocontainer 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-25 01:55:09 -06:00
Ian Eaves
3eeff04b2e type fixes 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 22:54:33 -06:00
Ian Eaves
51b83d4702 early return for dryrun 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 22:18:06 -06:00
Ian Eaves
a6633e3472 rebase + review 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 22:09:04 -06:00
Ian Eaves
8534297ebe pulled list out of try/except 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 22:06:52 -06:00
Ian Eaves
ed8bf43fe8 filter out unsupported payload values from dataclass on Benchmark records 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 22:06:52 -06:00
Ian Eaves
38e5e5cf8d adds benchmark metrics persistence 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 22:06:46 -06:00
Oliver Walsh
45f1556e42 Merge pull request #2192 from ramalama-labs/feat/chat-providers 
Add Provider Abstraction with support for Hosted API Calls
 2026-01-24 23:18:32 +00:00
Ian Eaves
ebfa498247 reverting docsite changes 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 17:11:03 -06:00
Ian Eaves
7bbcda466b adds model alias to api provider 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 16:29:44 -06:00
Ian Eaves
db8bb5d9df adds support for hosted chat providers 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-01-24 16:00:59 -06:00
red-hat-konflux-kflux-prd-rh03[bot]
3502813000 chore(deps): update konflux references 
Signed-off-by: red-hat-konflux-kflux-prd-rh03 <206760901+red-hat-konflux-kflux-prd-rh03[bot]@users.noreply.github.com>
 2026-01-24 08:49:45 +00:00
Mike Bonnet
b660d18382 update llama.cpp build flags 
Remove -DLLAMA_CURL=ON, llama.cpp no longer uses curl, the option is ignored. Remove
unused curl devel dependencies.
Remove unnecessary ARM_NEON defines.
Disable building of tests and examples for llama.cpp and ggml, for efficiency.

Signed-off-by: Mike Bonnet <mikeb@redhat.com>
 2026-01-24 00:35:21 -08:00
Mike Bonnet
028ae02d9c Merge pull request #2310 from olliewalsh/bump_llamacpp 
Bump llama.cpp and whisper.cpp version
 2026-01-23 22:53:08 -08:00
Oliver Walsh
87ab0b7ca6 Merge pull request #2311 from olliewalsh/fix_vllm 
Fix handling of alternative inference engines
 2026-01-24 02:30:35 +00:00
Oliver Walsh
ebe072fde1 Bump llama.cpp and whisper.cpp version 
Signed-off-by: Oliver Walsh <owalsh@redhat.com>
 2026-01-24 00:56:51 +00:00
Oliver Walsh
f37ec5cc88 Resolve review comments 
Signed-off-by: Oliver Walsh <owalsh@redhat.com>
 2026-01-24 00:53:04 +00:00
Oliver Walsh
aa7a271c73 Fix handling of inference spec which uses the image entrypoint 
Use a ContainerEntryPoint object in exec_args to indicate that
the entrypoint from the container image is used.
If so, skip this first arg when executing container commands and
omit the `command` field from the kube file podspectemplate.

Signed-off-by: Oliver Walsh <owalsh@redhat.com>
 2026-01-24 00:51:23 +00:00
Oliver Walsh
867e1e6865 Fix vLLM inference spec and chat client 
Omit the previous command ("binary" in the spec) as the vLLM images use the
entrypoint to run vLLM.

Fix --served-model-name option.
This refered to a non-existant model.model_name ctx variable.
Use model.alias instead.

Use precisely the same model name from the chat client.
vLLM will exit when this is not equal to the served-model-name.

Signed-off-by: Oliver Walsh <owalsh@redhat.com>
 2026-01-24 00:51:23 +00:00
Oliver Walsh
7965a5d22e Fix engine health check for vLLM 
The /models endpoint does not exist.
While there is a /v1/models endpoint, the data schema is also different.
For now just check the /ping endpoint when the runtime is vllm.

Signed-off-by: Oliver Walsh <owalsh@redhat.com>
 2026-01-24 00:51:23 +00:00
Oliver Walsh
621955d773 Fix --runtime cli arg parsing 
The --runtime are needs to be set before processing the inference spec,
otherwise the llama.cpp inference spec is used regardless of the runtime
specified on the cli.

Split the cli parsing into two phases:
In the first pass only the global args are parsed and the CONFIG object is
updated (setting runtime etc...).
In the second pass all subcommands are parsed too, which will process the
inference spec.

Signed-off-by: Oliver Walsh <owalsh@redhat.com>
 2026-01-24 00:51:23 +00:00
Oliver Walsh
05c9188851 Merge pull request #2342 from olliewalsh/chat_race 
Work around race condition in test/e2e/test_serve.py::test_serve_and_stop
 2026-01-24 00:49:56 +00:00
Oliver Walsh
a7c2a4e4fe Work around race condition in test/e2e/test_serve.py::test_serve_and_stop 
Signed-off-by: Oliver Walsh <owalsh@redhat.com>
 2026-01-24 00:47:25 +00:00
Oliver Walsh
2748d16aee Merge pull request #2333 from olliewalsh/winpath 
Fix remaining issues with Windows path handling and file URIs
 2026-01-24 00:39:15 +00:00
Oliver Walsh
93c8c91a70 Merge pull request #2341 from mikebonnet/konflux-volume-info 
konflux: use large disk instances for e2e tests
 2026-01-23 20:23:03 +00:00
Mike Bonnet
c410e99849 e2e, bats: use VM instances with 160G of disk space 
Signed-off-by: Mike Bonnet <mikeb@redhat.com>
 2026-01-23 09:48:42 -08:00
Mike Bonnet
807010a124 konflux: show mounts, volume sizes, and memory info on the remote VM 
Signed-off-by: Mike Bonnet <mikeb@redhat.com>
 2026-01-23 09:48:41 -08:00
Mike Bonnet
106a1e2eba Merge pull request #2326 from containers/konflux/mintmaker/main/docsite-lockfile-maintenance 
chore(deps): lock file maintenance
 2026-01-23 08:10:41 -08:00
Mike Bonnet
5211018ee9 Merge pull request #2337 from containers/konflux/mintmaker/main/wheel-0.x 
chore(deps): update dependency wheel to ~=0.46.3
 2026-01-23 08:08:15 -08:00
Oliver Walsh
a192d2ae9b Merge pull request #2302 from mikebonnet/macos-installer-manpages 
macOS installer: fixes and updates
 2026-01-23 11:41:52 +00:00
Oliver Walsh
12cd6fba86 Fix windows path and file uri issues 
Update e2e tests and re-enable all that were marked xfail on windows.

Ensure the ramalama run client and backend agree on the model name.

Enable windows long path support in CI as it was hitting the default 256
char limit.

Signed-off-by: Oliver Walsh <owalsh@redhat.com>
 2026-01-23 01:51:05 +00:00
Mike Bonnet
14a3108872 stop building and releasing the entrypoint images 
The entrypoint images are used by AI Lab, which pins to older digests and
has no need to update. Stop building and releasing new, unused versions.

Signed-off-by: Mike Bonnet <mikeb@redhat.com>
 2026-01-22 09:44:41 -08:00
red-hat-konflux-kflux-prd-rh03[bot]
9b814ca167 chore(deps): update dependency wheel to ~=0.46.3 
Signed-off-by: red-hat-konflux-kflux-prd-rh03 <206760901+red-hat-konflux-kflux-prd-rh03[bot]@users.noreply.github.com>
 2026-01-22 16:51:40 +00:00
Oliver Walsh
32432e6025 Merge pull request #2336 from mikebonnet/install-ollama-zstd 
ci: fix the ollama installer
 2026-01-22 13:03:13 +00:00
red-hat-konflux-kflux-prd-rh03[bot]
fb7918efbe chore(deps): lock file maintenance 
Signed-off-by: red-hat-konflux-kflux-prd-rh03 <206760901+red-hat-konflux-kflux-prd-rh03[bot]@users.noreply.github.com>
 2026-01-22 00:49:27 +00:00
Mike Bonnet
177d02f4b1 ci: fix the ollama installer 
ollama tarballs are now provided as .tar.zst, use the updated URL.

Add error handling and cleanup to the installation script.

Signed-off-by: Mike Bonnet <mikeb@redhat.com>
 2026-01-21 15:40:34 -08:00
Mike Bonnet
770957bde3 Merge pull request #2327 from containers/renovate/registry.access.redhat.com-ubi9-ubi-9.x 
chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1768785530
 2026-01-21 14:02:02 -08:00