Andreas KaratzasandOpenAI Codex
c6005000d3
Signed-off-by: Andreas Karatzas <akaratza@amd.com> Co-authored-by: OpenAI Codex <codex@openai.com>
5 lines
253 B
Plaintext
5 lines
253 B
Plaintext
# quantization, model, revision[, minimum capability[, safetensors load strategy]]
|
|
fp8, amd/Meta-Llama-3.1-70B-Instruct-FP8-KV, main, 80, prefetch
|
|
None, microsoft/phi-4, main, 80, prefetch
|
|
fp8, amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV, main, 80, prefetch
|