mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
feat: add embedding and dynamic model support to Together inference adapter (#3458)
# What does this PR do? adds embedding and dynamic model support to Together inference adapter - updated to use OpenAIMixin - workarounds for Together api quirks - recordings for together suite when subdirs=inference,pattern=openai ## Test Plan ``` $ TOGETHER_API_KEY=_NONE_ ./scripts/integration-tests.sh --stack-config server:ci-tests --setup together --subdirs inference --pattern openai ... tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:sanity] instantiating llama_stack_client Port 8321 is already in use, assuming server is already running... llama_stack_client instantiated in 0.121s PASSED [ 2%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:suffix] SKIPPED [ 4%] tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:sanity] PASSED [ 6%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-1] SKIPPED [ 8%] tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free] SKIPPED [ 10%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_01] PASSED [ 12%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] PASSED [ 14%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] SKIPPED [ 17%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 19%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 21%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free] SKIPPED [ 23%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 25%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 27%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 29%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 31%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 34%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 36%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 38%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 40%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 42%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 44%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-0] SKIPPED [ 46%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_02] PASSED [ 48%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] PASSED [ 51%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] SKIPPED [ 53%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 55%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 57%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 59%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 61%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 63%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 65%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 68%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 70%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 72%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 74%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 76%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 78%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_01] PASSED [ 80%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] PASSED [ 82%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] SKIPPED [ 85%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 87%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 89%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_02] PASSED [ 91%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] PASSED [ 93%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] SKIPPED [ 95%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 97%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [100%] ============================================ 30 passed, 17 skipped, 50 deselected, 4 warnings in 21.96s ============================================= ```
This commit is contained in:
Matthew Farrellee
GitHub
parent
3defdf7d3a
commit
49d4a5cc84
20 changed files with 9229 additions and 180 deletions
|
|
@ -4,7 +4,6 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.apis.models import ModelType
|
||||
from llama_stack.models.llama.sku_types import CoreModelId
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
ProviderModelEntry,
|
||||
|
|
@ -21,57 +20,84 @@ SAFETY_MODELS_ENTRIES = [
|
|||
CoreModelId.llama_guard_3_11b_vision.value,
|
||||
),
|
||||
]
|
||||
MODEL_ENTRIES = [
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
|
||||
CoreModelId.llama3_1_8b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
|
||||
CoreModelId.llama3_1_70b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
|
||||
CoreModelId.llama3_1_405b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-3.2-3B-Instruct-Turbo",
|
||||
CoreModelId.llama3_2_3b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
|
||||
CoreModelId.llama3_2_11b_vision_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
|
||||
CoreModelId.llama3_2_90b_vision_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-3.3-70B-Instruct-Turbo",
|
||||
CoreModelId.llama3_3_70b_instruct.value,
|
||||
),
|
||||
ProviderModelEntry(
|
||||
provider_model_id="togethercomputer/m2-bert-80M-8k-retrieval",
|
||||
model_type=ModelType.embedding,
|
||||
metadata={
|
||||
"embedding_dimension": 768,
|
||||
"context_length": 8192,
|
||||
},
|
||||
),
|
||||
ProviderModelEntry(
|
||||
|
||||
# source: https://docs.together.ai/docs/serverless-models#embedding-models
|
||||
EMBEDDING_MODEL_ENTRIES = {
|
||||
"togethercomputer/m2-bert-80M-32k-retrieval": ProviderModelEntry(
|
||||
provider_model_id="togethercomputer/m2-bert-80M-32k-retrieval",
|
||||
model_type=ModelType.embedding,
|
||||
metadata={
|
||||
"embedding_dimension": 768,
|
||||
"context_length": 32768,
|
||||
},
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-4-Scout-17B-16E-Instruct",
|
||||
CoreModelId.llama4_scout_17b_16e_instruct.value,
|
||||
"BAAI/bge-large-en-v1.5": ProviderModelEntry(
|
||||
provider_model_id="BAAI/bge-large-en-v1.5",
|
||||
metadata={
|
||||
"embedding_dimension": 1024,
|
||||
"context_length": 512,
|
||||
},
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
||||
CoreModelId.llama4_maverick_17b_128e_instruct.value,
|
||||
"BAAI/bge-base-en-v1.5": ProviderModelEntry(
|
||||
provider_model_id="BAAI/bge-base-en-v1.5",
|
||||
metadata={
|
||||
"embedding_dimension": 768,
|
||||
"context_length": 512,
|
||||
},
|
||||
),
|
||||
] + SAFETY_MODELS_ENTRIES
|
||||
"Alibaba-NLP/gte-modernbert-base": ProviderModelEntry(
|
||||
provider_model_id="Alibaba-NLP/gte-modernbert-base",
|
||||
metadata={
|
||||
"embedding_dimension": 768,
|
||||
"context_length": 8192,
|
||||
},
|
||||
),
|
||||
"intfloat/multilingual-e5-large-instruct": ProviderModelEntry(
|
||||
provider_model_id="intfloat/multilingual-e5-large-instruct",
|
||||
metadata={
|
||||
"embedding_dimension": 1024,
|
||||
"context_length": 512,
|
||||
},
|
||||
),
|
||||
}
|
||||
MODEL_ENTRIES = (
|
||||
[
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
|
||||
CoreModelId.llama3_1_8b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
|
||||
CoreModelId.llama3_1_70b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
|
||||
CoreModelId.llama3_1_405b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-3.2-3B-Instruct-Turbo",
|
||||
CoreModelId.llama3_2_3b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
|
||||
CoreModelId.llama3_2_11b_vision_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
|
||||
CoreModelId.llama3_2_90b_vision_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-3.3-70B-Instruct-Turbo",
|
||||
CoreModelId.llama3_3_70b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-4-Scout-17B-16E-Instruct",
|
||||
CoreModelId.llama4_scout_17b_16e_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
||||
CoreModelId.llama4_maverick_17b_128e_instruct.value,
|
||||
),
|
||||
]
|
||||
+ SAFETY_MODELS_ENTRIES
|
||||
+ list(EMBEDDING_MODEL_ENTRIES.values())
|
||||
)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue