[CI] Add DSV4-Flash to gsm8k moe-refactor/config-b200.txt (#42111)
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -0,0 +1,5 @@
|
||||
model_name: "deepseek-ai/DeepSeek-V4-Flash"
|
||||
accuracy_threshold: 0.95
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
server_args: "--trust-remote-code --kv-cache-dtype fp8 --block-size 256 --enable-expert-parallel --tensor-parallel-size 2 --attention_config.use_fp4_indexer_cache=True --moe-backend deep_gemm_mega_moe --tokenizer-mode deepseek_v4 --tool-call-parser deepseek_v4 --enable-auto-tool-choice --reasoning-parser deepseek_v4 --speculative_config.method=mtp --speculative_config.num_speculative_tokens=2"
|
||||
@@ -16,3 +16,4 @@ Mixtral-8x7B-BF16-triton.yaml
|
||||
Nemotron-Nano-30B-Fp8-ModelOpt-fi-trtllm.yaml
|
||||
Nemotron-Nano-30B-NvFp4-ModelOpt-fi-cutlass.yaml
|
||||
Nemotron-Nano-30B-NvFp4-ModelOpt-vllm-cutlass.yaml
|
||||
DeepSeek-V4-Flash-deepgemm-mega-moe.yaml
|
||||
|
||||
Reference in New Issue
Block a user