From c03438fc4e3b4617a4350a1da1974553b32dff3b Mon Sep 17 00:00:00 2001 From: biondizzle Date: Sun, 17 May 2026 16:25:38 +0000 Subject: [PATCH] crap shoot --- docker-compose.yml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docker-compose.yml b/docker-compose.yml index 30e5e48c..b93990f7 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -17,14 +17,15 @@ services: - --tensor-parallel-size=8 #- --enforce-eager - --compilation-config - #- '{"cudagraph_mode": "FULL_DECODE_ONLY", "custom_ops": ["all"], "cudagraph_capture_sizes": [1, 2, 4, 8], "max_cudagraph_capture_size": 8}' - - '{"cudagraph_mode":"FULL_AND_PIECEWISE", "custom_ops":["all"]}' + - '{"cudagraph_mode": "FULL_DECODE_ONLY", "custom_ops": ["all"], "cudagraph_capture_sizes": [1, 2, 4, 8], "max_cudagraph_capture_size": 8}' + #- '{"cudagraph_mode":"FULL_AND_PIECEWISE", "custom_ops":["all"]}' #- --moe-backend=deep_gemm_mega_moe - --tokenizer-mode=deepseek_v4 #- --attention_config.use_fp4_indexer_cache=True - --tool-call-parser=deepseek_v4 - --enable-auto-tool-choice - --reasoning-parser=deepseek_v4 + - --gpu_memory_utilization=0.9 - --host=0.0.0.0 - --port=8000 deploy: