vec-inf 0.5.0__py3-none-any.whl → 0.6.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- vec_inf/README.md +3 -3
- vec_inf/cli/_cli.py +214 -104
- vec_inf/cli/_helper.py +289 -564
- vec_inf/cli/_utils.py +26 -150
- vec_inf/cli/_vars.py +32 -0
- vec_inf/client/__init__.py +31 -0
- vec_inf/client/_client_vars.py +213 -0
- vec_inf/client/_exceptions.py +37 -0
- vec_inf/client/_helper.py +674 -0
- vec_inf/client/_slurm_script_generator.py +179 -0
- vec_inf/client/_utils.py +287 -0
- vec_inf/client/api.py +302 -0
- vec_inf/client/config.py +128 -0
- vec_inf/client/models.py +225 -0
- vec_inf/client/slurm_vars.py +49 -0
- vec_inf/config/README.md +0 -12
- vec_inf/config/models.yaml +417 -391
- {vec_inf-0.5.0.dist-info → vec_inf-0.6.0.dist-info}/METADATA +44 -61
- vec_inf-0.6.0.dist-info/RECORD +25 -0
- vec_inf/cli/_config.py +0 -87
- vec_inf/multinode_vllm.slurm +0 -154
- vec_inf/vllm.slurm +0 -90
- vec_inf-0.5.0.dist-info/RECORD +0 -17
- {vec_inf-0.5.0.dist-info → vec_inf-0.6.0.dist-info}/WHEEL +0 -0
- {vec_inf-0.5.0.dist-info → vec_inf-0.6.0.dist-info}/entry_points.txt +0 -0
- {vec_inf-0.5.0.dist-info → vec_inf-0.6.0.dist-info}/licenses/LICENSE +0 -0
vec_inf/config/README.md
CHANGED
|
@@ -24,12 +24,6 @@ More profiling metrics coming soon!
|
|
|
24
24
|
| [`CodeLlama-70b-hf`](https://huggingface.co/meta-llama/CodeLlama-70b-hf) | 4x a40 | - tokens/s | - tokens/s |
|
|
25
25
|
| [`CodeLlama-70b-Instruct-hf`](https://huggingface.co/meta-llama/CodeLlama-70b-Instruct-hf) | 4x a40 | - tokens/s | - tokens/s |
|
|
26
26
|
|
|
27
|
-
### [Databricks: DBRX](https://huggingface.co/collections/databricks/dbrx-6601c0852a0cdd3c59f71962)
|
|
28
|
-
|
|
29
|
-
| Variant | Suggested resource allocation | Avg prompt throughput | Avg generation throughput |
|
|
30
|
-
|:----------:|:----------:|:----------:|:----------:|
|
|
31
|
-
| [`dbrx-instruct`](https://huggingface.co/databricks/dbrx-instruct) | 8x a40 (2 nodes, 4 a40/node) | 107 tokens/s | 904 tokens/s |
|
|
32
|
-
|
|
33
27
|
### [Google: Gemma 2](https://huggingface.co/collections/google/gemma-2-release-667d6600fd5220e7b967f315)
|
|
34
28
|
|
|
35
29
|
| Variant | Suggested resource allocation | Avg prompt throughput | Avg generation throughput |
|
|
@@ -104,12 +98,6 @@ More profiling metrics coming soon!
|
|
|
104
98
|
|:----------:|:----------:|:----------:|:----------:|
|
|
105
99
|
| [`Phi-3-medium-128k-instruct`](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) | 2x a40 | - tokens/s | - tokens/s |
|
|
106
100
|
|
|
107
|
-
### [Aaditya Ura: Llama3-OpenBioLLM](https://huggingface.co/aaditya/Llama3-OpenBioLLM-70B)
|
|
108
|
-
|
|
109
|
-
| Variant | Suggested resource allocation | Avg prompt throughput | Avg generation throughput |
|
|
110
|
-
|:----------:|:----------:|:----------:|:----------:|
|
|
111
|
-
| [`Llama3-OpenBioLLM-70B`](https://huggingface.co/aaditya/Llama3-OpenBioLLM-70B) | 4x a40 | - tokens/s | - tokens/s |
|
|
112
|
-
|
|
113
101
|
### [Nvidia: Llama-3.1-Nemotron](https://huggingface.co/collections/nvidia/llama-31-nemotron-70b-670e93cd366feea16abc13d8)
|
|
114
102
|
|
|
115
103
|
| Variant | Suggested resource allocation | Avg prompt throughput | Avg generation throughput |
|