vllm/vllm_v0.10.0/.buildkite/lm-eval-harness/configs
hailin 38d813617c first commit 2025-08-03 20:28:19 +08:00
..
DeepSeek-V2-Lite-Chat.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-Instruct-FP8.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-Instruct.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-8B-QQQ.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3-70B-Instruct.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3.2-1B-Instruct-FP8-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Minitron-4B-Base-FP8.yaml first commit 2025-08-03 20:28:19 +08:00
Mixtral-8x7B-Instruct-v0.1-FP8.yaml first commit 2025-08-03 20:28:19 +08:00
Mixtral-8x7B-Instruct-v0.1.yaml first commit 2025-08-03 20:28:19 +08:00
Mixtral-8x22B-Instruct-v0.1-FP8-Dynamic.yaml first commit 2025-08-03 20:28:19 +08:00
Qwen1.5-MoE-W4A16-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Qwen2-1.5B-Instruct-FP8W8.yaml first commit 2025-08-03 20:28:19 +08:00
Qwen2-1.5B-Instruct-INT8-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Qwen2-1.5B-Instruct-W8A16-compressed-tensors.yaml first commit 2025-08-03 20:28:19 +08:00
Qwen2-57B-A14-Instruct.yaml first commit 2025-08-03 20:28:19 +08:00
Qwen2.5-1.5B-Instruct.yaml first commit 2025-08-03 20:28:19 +08:00
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml first commit 2025-08-03 20:28:19 +08:00
SparseLlama3.1_2of4_fp8_compressed.yaml first commit 2025-08-03 20:28:19 +08:00
models-large.txt first commit 2025-08-03 20:28:19 +08:00
models-small.txt first commit 2025-08-03 20:28:19 +08:00