20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Doc] Replace ibm-fms with ibm-ai-platform (#12709)

Browse Source 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
This commit is contained in:
Thomas Parnell 2025-02-04 02:05:04 -05:00 committed by GitHub
parent 5d98d56089
commit bb392af434
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
docs/source/features/spec_decode.md
View File

@ -131,7 +131,7 @@ sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM( llm = LLM(
model="meta-llama/Meta-Llama-3.1-70B-Instruct", model="meta-llama/Meta-Llama-3.1-70B-Instruct",
tensor_parallel_size=4, tensor_parallel_size=4,
speculative_model="ibm-fms/llama3-70b-accelerator", speculative_model="ibm-ai-platform/llama3-70b-accelerator",
speculative_draft_tensor_parallel_size=1, speculative_draft_tensor_parallel_size=1,
) )
outputs = llm.generate(prompts, sampling_params) outputs = llm.generate(prompts, sampling_params)
@ -149,11 +149,11 @@ limitation will be fixed in a future release.
A variety of speculative models of this type are available on HF hub: A variety of speculative models of this type are available on HF hub:
- [llama-13b-accelerator](https://huggingface.co/ibm-fms/llama-13b-accelerator) - [llama-13b-accelerator](https://huggingface.co/ibm-ai-platform/llama-13b-accelerator)
- [llama3-8b-accelerator](https://huggingface.co/ibm-fms/llama3-8b-accelerator) - [llama3-8b-accelerator](https://huggingface.co/ibm-ai-platform/llama3-8b-accelerator)
- [codellama-34b-accelerator](https://huggingface.co/ibm-fms/codellama-34b-accelerator) - [codellama-34b-accelerator](https://huggingface.co/ibm-ai-platform/codellama-34b-accelerator)
- [llama2-70b-accelerator](https://huggingface.co/ibm-fms/llama2-70b-accelerator) - [llama2-70b-accelerator](https://huggingface.co/ibm-ai-platform/llama2-70b-accelerator)
- [llama3-70b-accelerator](https://huggingface.co/ibm-fms/llama3-70b-accelerator) - [llama3-70b-accelerator](https://huggingface.co/ibm-ai-platform/llama3-70b-accelerator)
- [granite-3b-code-instruct-accelerator](https://huggingface.co/ibm-granite/granite-3b-code-instruct-accelerator) - [granite-3b-code-instruct-accelerator](https://huggingface.co/ibm-granite/granite-3b-code-instruct-accelerator)
- [granite-8b-code-instruct-accelerator](https://huggingface.co/ibm-granite/granite-8b-code-instruct-accelerator) - [granite-8b-code-instruct-accelerator](https://huggingface.co/ibm-granite/granite-8b-code-instruct-accelerator)
- [granite-7b-instruct-accelerator](https://huggingface.co/ibm-granite/granite-7b-instruct-accelerator) - [granite-7b-instruct-accelerator](https://huggingface.co/ibm-granite/granite-7b-instruct-accelerator)

2
examples/offline_inference/mlpspeculator.py
View File

@ -51,7 +51,7 @@ if __name__ == "__main__":
# Create an LLM with spec decoding # Create an LLM with spec decoding
llm = LLM( llm = LLM(
model="meta-llama/Llama-2-13b-chat-hf", model="meta-llama/Llama-2-13b-chat-hf",
speculative_model="ibm-fms/llama-13b-accelerator", speculative_model="ibm-ai-platform/llama-13b-accelerator",
) )
print("With speculation") print("With speculation")

2
tests/models/registry.py
View File

@ -278,7 +278,7 @@ _SPECULATIVE_DECODING_EXAMPLE_MODELS = {
"MedusaModel": _HfExamplesInfo("JackFram/llama-68m", "MedusaModel": _HfExamplesInfo("JackFram/llama-68m",
speculative_model="abhigoyal/vllm-medusa-llama-68m-random"), # noqa: E501 speculative_model="abhigoyal/vllm-medusa-llama-68m-random"), # noqa: E501
"MLPSpeculatorPreTrainedModel": _HfExamplesInfo("JackFram/llama-160m", "MLPSpeculatorPreTrainedModel": _HfExamplesInfo("JackFram/llama-160m",
speculative_model="ibm-fms/llama-160m-accelerator"), # noqa: E501 speculative_model="ibm-ai-platform/llama-160m-accelerator"), # noqa: E501
} }
_FALLBACK_MODEL = { _FALLBACK_MODEL = {

2
tests/spec_decode/e2e/test_mlp_correctness.py
View File

@ -33,7 +33,7 @@ from .conftest import run_equality_correctness_test
MAIN_MODEL = "JackFram/llama-160m" MAIN_MODEL = "JackFram/llama-160m"
# speculative model # speculative model
SPEC_MODEL = "ibm-fms/llama-160m-accelerator" SPEC_MODEL = "ibm-ai-platform/llama-160m-accelerator"
# max. number of speculative tokens: this corresponds to # max. number of speculative tokens: this corresponds to
# n_predict in the config.json of the speculator model. # n_predict in the config.json of the speculator model.

2
vllm/model_executor/models/mlp_speculator.py
View File

@ -64,7 +64,7 @@ class MLPSpeculator(nn.Module):
https://arxiv.org/pdf/2404.19124 https://arxiv.org/pdf/2404.19124
Trained speculators of this type are available on HF hub at: Trained speculators of this type are available on HF hub at:
https://huggingface.co/ibm-fms and https://huggingface.co/ibm-granite https://huggingface.co/ibm-ai-platform and https://huggingface.co/ibm-granite
""" """
def __init__(self, *, vllm_config: VllmConfig, prefix: str = "") -> None: def __init__(self, *, vllm_config: VllmConfig, prefix: str = "") -> None: