issues
search
chenhunghan
/
ialacol
🪶 Lightweight OpenAI drop-in replacement for Kubernetes
MIT License
143
stars
17
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Bump fastapi from 0.95.2 to 0.109.1
#95
dependabot[bot]
opened
9 months ago
0
Bump starlette from 0.27.0 to 0.36.2
#94
dependabot[bot]
opened
9 months ago
0
feat: rewritten to Rust/WASM with wasm-edge + wasi-nn-ggml
#93
chenhunghan
opened
9 months ago
0
Bump aiohttp from 3.9.0 to 3.9.2 in /examples/openai
#92
dependabot[bot]
opened
10 months ago
0
Fix/add annotations to service template
#91
donbale
closed
10 months ago
1
added-annotations-to-service-template
#90
donbale
closed
10 months ago
1
Add rust toolchain to fix docker image build
#89
chenhunghan
closed
11 months ago
0
Fix image build 'Multiple platforms feature is currently not supporte…
#88
chenhunghan
closed
11 months ago
0
add support for arm architecture for published images
#87
damianoneill
closed
11 months ago
0
Question: Does ialacol support multi-arch?
#86
damianoneill
closed
11 months ago
1
Bump aiohttp from 3.8.6 to 3.9.0 in /examples/openai
#85
dependabot[bot]
closed
1 year ago
0
Usage gpu_layers with ialacol-metal provides an error
#84
VirtualRoyalty
opened
1 year ago
0
Bump aiohttp from 3.8.5 to 3.8.6 in /examples/openai
#83
dependabot[bot]
closed
1 year ago
0
Add support for OpenChat 3.5/Zephyr 7B β, improve fallbacks of `repetition_penalty`, support multiple messages in request body
#82
chenhunghan
closed
1 year ago
0
Create devcontainer.json
#81
chenhunghan
closed
1 year ago
0
Upgrade hg-hub to 0.17.3
#80
chenhunghan
opened
1 year ago
0
Bump urllib3 from 2.0.6 to 2.0.7
#79
dependabot[bot]
closed
1 year ago
0
Bump urllib3 from 2.0.6 to 2.0.7 in /examples/openai
#78
dependabot[bot]
closed
1 year ago
0
Add support for download model from a specific revision
#77
chenhunghan
closed
1 year ago
0
Unable to download HG model from specific branch in helm chart
#76
thearchitectxy
closed
1 year ago
5
Plan to support AWQ models
#75
thearchitectxy
closed
1 year ago
1
Mix streamings and threads count for GPTQ Models bug
#74
thearchitectxy
closed
1 year ago
4
Bump urllib3 from 2.0.2 to 2.0.6
#73
dependabot[bot]
closed
1 year ago
0
Bump urllib3 from 2.0.2 to 2.0.6 in /examples/openai
#72
dependabot[bot]
closed
1 year ago
0
Add support for mistral ai's instruct model, avoid system start token duplicate, remove extra log
#71
chenhunghan
closed
1 year ago
0
`CONTEXT_LENGTH` default to 4096, and warning for context, add 422 logger, refactor prompt template
#70
chenhunghan
closed
1 year ago
0
Add defaults/warning for max-tokens and context-length, document env vars
#69
chenhunghan
closed
1 year ago
0
Upgrade ctransformer to v0.2.27
#68
chenhunghan
closed
1 year ago
0
Auto detecting threads
#67
3deep5me
closed
1 year ago
2
ctransformer to 0.2.26
#66
chenhunghan
closed
1 year ago
0
Support GPTQ via Transformer instead of Exllama/ctransformer
#65
chenhunghan
closed
1 year ago
0
Fixes for gptq image, improve `codegen` mapping (to gptj)
#64
chenhunghan
closed
1 year ago
0
Pass `TRUNCATE_PROMPT_LENGTH` to deployment, switch to `ghcr.io` image
#63
chenhunghan
closed
1 year ago
0
Add support for VSCode Github Copilot
#62
chenhunghan
closed
1 year ago
0
Reduce memory usage for large models
#61
chenhunghan
closed
1 year ago
0
Fix chart version
#60
chenhunghan
closed
1 year ago
0
Add example `codellama.yaml`, ctransformer to 0.2.24, refactor `get_config`
#59
chenhunghan
closed
1 year ago
0
Downloading models fail with timeouts, retry is not enabled.
#58
DavidARivkin
closed
1 year ago
3
Deployment fails to respond with errors
#57
DavidARivkin
closed
1 year ago
1
Allow to mount existing pvc
#56
chenhunghan
opened
1 year ago
0
Add default Liveness, Readiness and Startup probes
#55
chenhunghan
opened
1 year ago
0
Use quay.io for storing smoke test images
#54
chenhunghan
closed
1 year ago
0
Add `pythia` matching, push base image to ghrc.io, remove `modelMountPath`/`cacheMountPath`, merge volumes, update README
#53
chenhunghan
closed
1 year ago
0
Support stablecode, improve gpt-neox CI
#52
chenhunghan
closed
1 year ago
0
Upgrade ctransformer to 0.2.22, add GPUT support for StarCoder, make …
#51
chenhunghan
closed
1 year ago
0
Add experimental support for GPTQ models
#50
chenhunghan
closed
1 year ago
0
Add experimental metal support
#49
chenhunghan
closed
1 year ago
0
Fix Helm deployment template, add missing env variables, fix logger
#48
chenhunghan
closed
1 year ago
0
Support GPTQ model
#47
chenhunghan
closed
1 year ago
0
Fix the cuda 12 base image
#46
chenhunghan
closed
1 year ago
0
Next