ruihan/qwen38-flash-next-dgx-spark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Set 128K eager baseline and organize deployment documentation

Browse Source
This commit is contained in:
ruihan
2026-09-18 01:33:57 +08:00
parent d7e1e745c3
commit e290793f2b
15 changed files with 98 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
experiments/graph/compose.prefix.yaml
+1 -1
View File
@@ -12,7 +12,7 @@ services:
--tensor-parallel-size 1
--dtype bfloat16 --kv-cache-dtype auto
--gpu-memory-utilization ${GPU_MEMORY_UTILIZATION:-0.80}
--max-model-len 262144 --max-num-seqs ${MAX_NUM_SEQS:-4} --max-num-batched-tokens 2048
--max-model-len 131072 --max-num-seqs ${MAX_NUM_SEQS:-4} --max-num-batched-tokens 2048
--enable-chunked-prefill --enable-prefix-caching
--speculative-config '{"method":"mtp","num_speculative_tokens":2}'
--compilation-config '{"mode":3,"cudagraph_mode":"PIECEWISE","splitting_ops":["vllm::unified_attention_with_output","vllm::unified_mla_attention_with_output","vllm::mamba_mixer2","vllm::mamba_mixer","vllm::short_conv","vllm::qwen4_exp_ple_short_conv","vllm::qwen4_exp_qsa_with_output","vllm::linear_attention","vllm::qwen_gdn_attention_core","vllm::qwen_gdn_attention_core_fused_norm_packed","vllm::gdn_attention_core_xpu","vllm::olmo_hybrid_gdn_full_forward","vllm::sparse_attn_indexer","vllm::rocm_aiter_sparse_attn_indexer","vllm::deepseek_v4_attention","vllm::hpc_rope_norm_forward","vllm::unified_kv_cache_update","vllm::unified_mla_kv_cache_update","vllm::spark_ple_lookup"],"cudagraph_capture_sizes":[1,2,4,8,12]}' --no-enable-flashinfer-autotune
experiments/graph/compose.yaml
+1 -1
View File
@@ -12,7 +12,7 @@ services:
--tensor-parallel-size 1
--dtype bfloat16 --kv-cache-dtype auto
--gpu-memory-utilization ${GPU_MEMORY_UTILIZATION:-0.80}
--max-model-len 262144 --max-num-seqs ${MAX_NUM_SEQS:-4} --max-num-batched-tokens 2048
--max-model-len 131072 --max-num-seqs ${MAX_NUM_SEQS:-4} --max-num-batched-tokens 2048
--enable-chunked-prefill --no-enable-prefix-caching
--speculative-config '{"method":"mtp","num_speculative_tokens":2}'
--compilation-config '{"mode":3,"cudagraph_mode":"PIECEWISE","splitting_ops":["vllm::unified_attention_with_output","vllm::unified_mla_attention_with_output","vllm::mamba_mixer2","vllm::mamba_mixer","vllm::short_conv","vllm::qwen4_exp_ple_short_conv","vllm::qwen4_exp_qsa_with_output","vllm::linear_attention","vllm::qwen_gdn_attention_core","vllm::qwen_gdn_attention_core_fused_norm_packed","vllm::gdn_attention_core_xpu","vllm::olmo_hybrid_gdn_full_forward","vllm::sparse_attn_indexer","vllm::rocm_aiter_sparse_attn_indexer","vllm::deepseek_v4_attention","vllm::hpc_rope_norm_forward","vllm::unified_kv_cache_update","vllm::unified_mla_kv_cache_update","vllm::spark_ple_lookup"],"cudagraph_capture_sizes":[1,2,4,8,12]}' --no-enable-flashinfer-autotune