Skip to content

Commit

Permalink
Updated R1s config. Updated README accordingly.
Browse files Browse the repository at this point in the history
  • Loading branch information
kohankhaki committed Feb 14, 2025
1 parent ad2425f commit 9032747
Show file tree
Hide file tree
Showing 2 changed files with 8 additions and 8 deletions.
8 changes: 4 additions & 4 deletions vec_inf/models/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -152,12 +152,12 @@ More profiling metrics coming soon!

| Variant | Suggested resource allocation | Avg prompt throughput | Avg generation throughput |
|:----------:|:----------:|:----------:|:----------:|
| [`DeepSeek-R1-Distill-Llama-70B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) | 4x a40 | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Llama-8B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) | 1x a40 | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Qwen-32B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) | 2x a40 | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Qwen-14B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) | 1x a40 | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Qwen-7B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | 1x a40 | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Llama-70B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) | 8x a40 (2 nodes, 4 a40/node) | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Qwen-1.5B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) | 1x a40 | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Qwen-7B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | 1x a40 | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Qwen-14B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) | 2x a40 | - tokens/s | - tokens/s |
| [`DeepSeek-R1-Distill-Qwen-32B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) | 4x a40 | - tokens/s | - tokens/s |


## Vision Language Models
Expand Down
8 changes: 4 additions & 4 deletions vec_inf/models/models.csv
Original file line number Diff line number Diff line change
Expand Up @@ -77,9 +77,9 @@ Llama-3.3-70B-Instruct,Llama-3.3,70B-Instruct,LLM,4,1,128256,65536,256,true,fals
InternVL2_5-26B,InternVL2_5,26B,VLM,2,1,92553,32768,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
InternVL2_5-38B,InternVL2_5,38B,VLM,4,1,92553,32768,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
Aya-Expanse-32B,Aya-Expanse,32B,LLM,2,1,256000,8192,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Llama-70B,DeepSeek-R1,Distill-Llama-70B ,LLM,4,1,128256,65536,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Llama-8B,DeepSeek-R1,Distill-Llama-8B ,LLM,1,1,128256,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Qwen-32B,DeepSeek-R1,Distill-Qwen-32B,LLM,2,1,152064,65536,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Qwen-14B,DeepSeek-R1,Distill-Qwen-14B,LLM,1,1,152064,65536,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Llama-70B,DeepSeek-R1,Distill-Llama-70B,LLM,4,2,128256,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Llama-8B,DeepSeek-R1,Distill-Llama-8B,LLM,1,1,128256,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Qwen-32B,DeepSeek-R1,Distill-Qwen-32B,LLM,4,1,152064,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Qwen-14B,DeepSeek-R1,Distill-Qwen-14B,LLM,2,1,152064,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Qwen-7B,DeepSeek-R1,Distill-Qwen-7B,LLM,1,1,152064,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
DeepSeek-R1-Distill-Qwen-1.5B,DeepSeek-R1,Distill-Qwen-1.5B,LLM,1,1,152064,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights

0 comments on commit 9032747

Please sign in to comment.