Index of /ia/ssd/workspace/git/vllm/tests/evals/gsm8k/configs/moe-refactor
Name
Last modified
Size
Description
Parent Directory
-
DeepSeek-V4-Flash-deepgemm-mega-moe.yaml
2026-05-22 19:01
501
Llama-4-Scout-BF16-fi-cutlass.yaml
2026-05-13 15:24
251
Llama-4-Scout-BF16-triton.yaml
2026-05-13 15:24
194
Llama-4-Scout-Fp8-CT-vllm-cutlass.yaml
2026-05-13 15:24
203
Llama-4-Scout-Fp8-ModelOpt-fi-cutlass.yaml
2026-05-13 15:24
226
Llama-4-Scout-Fp8-ModelOpt-fi-trtllm.yaml
2026-05-13 15:24
225
Llama-4-Scout-Fp8-ModelOpt-marlin.yaml
2026-05-13 15:24
232
Llama-4-Scout-Fp8-ModelOpt-triton.yaml
2026-05-13 15:24
214
Mixtral-8x7B-BF16-fi-cutlass.yaml
2026-05-13 15:24
237
Mixtral-8x7B-BF16-triton.yaml
2026-05-13 15:24
179
Mixtral-8x7B-Fp8-AutoFp8-fi-cutlass.yaml
2026-05-13 15:24
252
Mixtral-8x7B-Fp8-AutoFp8-triton.yaml
2026-05-13 15:24
189
Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml
2026-05-13 15:24
225
Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml
2026-05-13 15:24
228
Nemotron-Nano-30B-NvFp4-ModelOpt-vllm-cutlass.yaml
2026-05-13 15:24
217
Qwen3-30B-A3B-BF16-fi-cutlass.yaml
2026-05-13 15:24
228
Qwen3-30B-A3B-BF16-triton.yaml
2026-05-13 15:24
170
Qwen3-30B-A3B-Fp8-AutoFp8-deepgemm.yaml
2026-05-13 15:24
250
Qwen3-30B-A3B-Fp8-AutoFp8-fi-cutlass.yaml
2026-05-13 15:24
222
Qwen3-30B-A3B-Fp8-AutoFp8-fi-trtllm.yaml
2026-05-13 15:24
221
Qwen3-30B-A3B-Fp8-AutoFp8-marlin.yaml
2026-05-13 15:24
228
Qwen3-30B-A3B-Fp8-AutoFp8-triton.yaml
2026-05-13 15:24
241
Qwen3-30B-A3B-Fp8-CT-Block-deepgemm.yaml
2026-05-13 15:24
245
Qwen3-30B-A3B-Fp8-CT-Block-fi-cutlass.yaml
2026-05-13 15:24
217
Qwen3-30B-A3B-Fp8-CT-Block-marlin.yaml
2026-05-13 15:24
223
Qwen3-30B-A3B-Fp8-CT-Block-triton.yaml
2026-05-13 15:24
236
Qwen3-30B-A3B-Fp8-CT-Channel-marlin.yaml
2026-05-13 15:24
225
Qwen3-30B-A3B-Fp8-CT-Channel-vllm-cutlass.yaml
2026-05-13 15:24
186
Qwen3-30B-A3B-NvFp4-CT-fi-cutlass.yaml
2026-05-13 15:24
213
Qwen3-30B-A3B-NvFp4-CT-fi-trtllm.yaml
2026-05-13 15:24
212
Qwen3-30B-A3B-NvFp4-CT-marlin.yaml
2026-05-13 15:24
219
Qwen3-30B-A3B-NvFp4-CT-vllm-cutlass.yaml
2026-05-13 15:24
202
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-cutlass.yaml
2026-05-13 15:24
211
Qwen3-30B-A3B-NvFp4-ModelOpt-fi-trtllm.yaml
2026-05-13 15:24
210
Qwen3-30B-A3B-NvFp4-ModelOpt-marlin.yaml
2026-05-13 15:24
217
Qwen3-30B-A3B-NvFp4-ModelOpt-vllm-cutlass.yaml
2026-05-13 15:24
200
config-b200.txt
2026-05-22 19:01
771
config-h100.txt
2026-05-13 15:24
468
config-test.txt
2026-05-13 15:24
34
Apache/2.4.68 (Debian) Server at 192.168.0.22 Port 80