Aaron Pham 85a7243ac3 fix: device imports using strategies (#584) ...

* fix: device imports using strategies

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* chore: support trust_remote_code for vLLM runners

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

2023-11-08 05:10:50 -05:00

..

bundle

fix: device imports using strategies (#584)

2023-11-08 05:10:50 -05:00

cli

refactor(strategies): move logics into openllm-python (#578)

2023-11-08 02:23:08 -05:00

entrypoints

refactor: cleanup typing to expose correct API (#576)

2023-11-08 01:24:03 -05:00

playground

chore(runner): yield the outputs directly (#573)

2023-11-07 22:34:11 -05:00

protocol

refactor: cleanup typing to expose correct API (#576)

2023-11-08 01:24:03 -05:00

serialisation

refactor: cleanup typing to expose correct API (#576)

2023-11-08 01:24:03 -05:00

utils

fix: device imports using strategies (#584)

2023-11-08 05:10:50 -05:00

__init__.py

chore(service): cleanup API (#579)

2023-11-08 02:53:08 -05:00

__main__.py

refactor: cleanup typing to expose correct API (#576)

2023-11-08 01:24:03 -05:00

_deprecated.py

perf: unify LLM interface (#518)

2023-11-06 20:39:43 -05:00

_generation.py

refactor: cleanup typing to expose correct API (#576)

2023-11-08 01:24:03 -05:00

_llm.py

chore(service): cleanup API (#579)

2023-11-08 02:53:08 -05:00

_quantisation.py

perf: unify LLM interface (#518)

2023-11-06 20:39:43 -05:00

_runners.py

fix: device imports using strategies (#584)

2023-11-08 05:10:50 -05:00

_service_vars_pkg.py

perf: unify LLM interface (#518)

2023-11-06 20:39:43 -05:00

_service_vars.py

perf: unify LLM interface (#518)

2023-11-06 20:39:43 -05:00

_service.py

chore(service): cleanup API (#579)

2023-11-08 02:53:08 -05:00

_strategies.py

chore(service): cleanup API (#579)

2023-11-08 02:53:08 -05:00

client.py

fix(breaking): remove embeddings and update client implementation (#500)

2023-10-14 16:04:35 -04:00

exceptions.py

refactor: cleanup typing to expose correct API (#576)

2023-11-08 01:24:03 -05:00

prompts.py

feat: PromptTemplate and system prompt support (#407)

2023-10-03 09:53:37 -04:00

py.typed

refactor: monorepo (#203)

2023-08-15 02:11:14 -04:00

testing.py

refactor: cleanup typing to expose correct API (#576)

2023-11-08 01:24:03 -05:00