From 0c89fd4fbea0db9db2071df2f78403c64c3bc466 Mon Sep 17 00:00:00 2001
From: yy-fighting <2351884576@qq.com>
Date: Wed, 9 Sep 2026 09:24:43 +0800
Subject: [PATCH] r37 addendum: nomtp sweep raw logs (primary evidence,
 force-added past *.log ignore)

---
 .../results/nomtp_sweep_all.log               | 36 ++++++++++++
 .../results/nomtpsweep_cc16.log               | 56 +++++++++++++++++++
 .../results/nomtpsweep_cc32.log               | 56 +++++++++++++++++++
 .../results/nomtpsweep_cc40.log               | 56 +++++++++++++++++++
 .../results/nomtpsweep_cc64.log               | 56 +++++++++++++++++++
 .../results/nomtpsweep_cc8.log                | 56 +++++++++++++++++++
 6 files changed, 316 insertions(+)
 create mode 100644 experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtp_sweep_all.log
 create mode 100644 experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc16.log
 create mode 100644 experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc32.log
 create mode 100644 experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc40.log
 create mode 100644 experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc64.log
 create mode 100644 experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc8.log

diff --git a/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtp_sweep_all.log b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtp_sweep_all.log
new file mode 100644
index 0000000..b2b7cc1
--- /dev/null
+++ b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtp_sweep_all.log
@@ -0,0 +1,36 @@
+=== cc=8 nreq=16 seed=6508 start 08:47:29 ===
+=== cc=8 done rc=0 08:49:27 ===
+Successful requests:                     16        
+Benchmark duration (s):                  78.92     
+Output token throughput (tok/s):         103.81    
+Mean TTFT (ms):                          18179.50  
+Mean TPOT (ms):                          41.59     
+=== cc=16 nreq=32 seed=6516 start 08:49:27 ===
+=== cc=16 done rc=0 08:52:00 ===
+Successful requests:                     32        
+Benchmark duration (s):                  128.71    
+Output token throughput (tok/s):         127.29    
+Mean TTFT (ms):                          30898.35  
+Mean TPOT (ms):                          48.53     
+=== cc=32 nreq=64 seed=6532 start 08:52:00 ===
+=== cc=32 done rc=0 08:56:29 ===
+Successful requests:                     64        
+Benchmark duration (s):                  244.71    
+Output token throughput (tok/s):         133.91    
+Mean TTFT (ms):                          74930.30  
+Mean TPOT (ms):                          48.54     
+=== cc=40 nreq=80 seed=6540 start 08:56:29 ===
+=== cc=40 done rc=0 09:02:00 ===
+Successful requests:                     80        
+Benchmark duration (s):                  304.60    
+Output token throughput (tok/s):         134.47    
+Mean TTFT (ms):                          93857.54  
+Mean TPOT (ms):                          53.23     
+=== cc=64 nreq=128 seed=6564 start 09:02:00 ===
+=== cc=64 done rc=0 09:10:18 ===
+Successful requests:                     128       
+Benchmark duration (s):                  473.55    
+Output token throughput (tok/s):         138.39    
+Mean TTFT (ms):                          161310.10 
+Mean TPOT (ms):                          50.23     
+SWEEP-DONE
diff --git a/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc16.log b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc16.log
new file mode 100644
index 0000000..ba7d83f
--- /dev/null
+++ b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc16.log
@@ -0,0 +1,56 @@
+/sgl-workspace/sglang/python/sglang/bench_serving.py:13: FutureWarning: `sglang.bench_serving` is deprecated and will be removed in a future release; use `sglang.benchmark.serving` instead (e.g. `python -m sglang.benchmark.serving`).
+  warnings.warn(
+benchmark_args=Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model=None, served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=32, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=16, output_file='/data/hf_models/bs_results/nomtpsweep_cc16.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6516, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+Waiting up to 60s for http://127.0.0.1:30000/v1/models to become ready...
+Server ready in 0.0s.
+Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model='/data/hf_models/GLM-5.3-NVFP4', served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=32, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=16, output_file='/data/hf_models/bs_results/nomtpsweep_cc16.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6516, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+
+#Input tokens: 524288
+#Output tokens: 16384
+Starting warmup with 1 sequences...
+Warmup completed with 1 sequences. Starting main benchmark run...
+
  0%|          | 0/32 [00:00<?, ?it/s]
  3%|▎         | 1/32 [00:54<28:03, 54.29s/it]
 50%|█████     | 16/32 [01:48<01:34,  5.90s/it]
 75%|███████▌  | 24/32 [01:49<00:27,  3.42s/it]
 94%|█████████▍| 30/32 [02:00<00:06,  3.42s/it]
 97%|█████████▋| 31/32 [02:08<00:03,  3.21s/it]
100%|██████████| 32/32 [02:08<00:00,  4.02s/it]
+
+============ Serving Benchmark Result ============
+Backend:                                 sglang    
+Traffic request rate:                    inf       
+Max request concurrency:                 16        
+Successful requests:                     32        
+Benchmark duration (s):                  128.71    
+Total input tokens:                      524288    
+Total input text tokens:                 524288    
+Total generated tokens:                  16384     
+Total generated tokens (retokenized):    16382     
+Request throughput (req/s):              0.25      
+Input token throughput (tok/s):          4073.29   
+Output token throughput (tok/s):         127.29    
+Peak output token throughput (tok/s):    368.00    
+Peak concurrent requests:                31        
+Total token throughput (tok/s):          4200.58   
+Concurrency:                             13.85     
+----------------End-to-End Latency----------------
+Mean E2E Latency (ms):                   55694.74  
+Median E2E Latency (ms):                 54445.67  
+P90 E2E Latency (ms):                    54686.04  
+P95 E2E Latency (ms):                    63545.86  
+P99 E2E Latency (ms):                    98164.60  
+---------------Time to First Token----------------
+Mean TTFT (ms):                          30898.35  
+Median TTFT (ms):                        32450.28  
+P90 TTFT (ms):                           32916.51  
+P95 TTFT (ms):                           44236.01  
+P99 TTFT (ms):                           59379.03  
+-----Time per Output Token (excl. 1st token)------
+Mean TPOT (ms):                          48.53     
+Median TPOT (ms):                        43.40     
+P90 TPOT (ms):                           77.67     
+P95 TPOT (ms):                           84.84     
+P99 TPOT (ms):                           95.77     
+---------------Inter-Token Latency----------------
+Mean ITL (ms):                           48.59     
+Median ITL (ms):                         42.63     
+P90 ITL (ms):                            43.95     
+P95 ITL (ms):                            44.32     
+P99 ITL (ms):                            44.93     
+Max ITL (ms):                            28619.03  
+==================================================
diff --git a/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc32.log b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc32.log
new file mode 100644
index 0000000..fa112f5
--- /dev/null
+++ b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc32.log
@@ -0,0 +1,56 @@
+/sgl-workspace/sglang/python/sglang/bench_serving.py:13: FutureWarning: `sglang.bench_serving` is deprecated and will be removed in a future release; use `sglang.benchmark.serving` instead (e.g. `python -m sglang.benchmark.serving`).
+  warnings.warn(
+benchmark_args=Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model=None, served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=64, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=32, output_file='/data/hf_models/bs_results/nomtpsweep_cc32.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6532, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+Waiting up to 60s for http://127.0.0.1:30000/v1/models to become ready...
+Server ready in 0.0s.
+Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model='/data/hf_models/GLM-5.3-NVFP4', served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=64, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=32, output_file='/data/hf_models/bs_results/nomtpsweep_cc32.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6532, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+
+#Input tokens: 1048576
+#Output tokens: 32768
+Starting warmup with 1 sequences...
+Warmup completed with 1 sequences. Starting main benchmark run...
+
  0%|          | 0/64 [00:00<?, ?it/s]
  2%|▏         | 1/64 [00:54<57:21, 54.63s/it]
 25%|██▌       | 16/64 [01:49<04:44,  5.92s/it]
 38%|███▊      | 24/64 [01:49<02:17,  3.43s/it]
 47%|████▋     | 30/64 [02:00<01:56,  3.43s/it]
 48%|████▊     | 31/64 [02:43<02:42,  4.93s/it]
 61%|██████    | 39/64 [02:44<01:19,  3.16s/it]
 70%|███████   | 45/64 [03:00<01:00,  3.16s/it]
 72%|███████▏  | 46/64 [03:38<01:22,  4.58s/it]
 95%|█████████▌| 61/64 [04:04<00:09,  3.21s/it]
100%|██████████| 64/64 [04:04<00:00,  3.82s/it]
+
+============ Serving Benchmark Result ============
+Backend:                                 sglang    
+Traffic request rate:                    inf       
+Max request concurrency:                 32        
+Successful requests:                     64        
+Benchmark duration (s):                  244.71    
+Total input tokens:                      1048576   
+Total input text tokens:                 1048576   
+Total generated tokens:                  32768     
+Total generated tokens (retokenized):    32754     
+Request throughput (req/s):              0.26      
+Input token throughput (tok/s):          4285.04   
+Output token throughput (tok/s):         133.91    
+Peak output token throughput (tok/s):    360.00    
+Peak concurrent requests:                47        
+Total token throughput (tok/s):          4418.95   
+Concurrency:                             26.08     
+----------------End-to-End Latency----------------
+Mean E2E Latency (ms):                   99736.29  
+Median E2E Latency (ms):                 109235.40 
+P90 E2E Latency (ms):                    109445.39 
+P95 E2E Latency (ms):                    159345.69 
+P99 E2E Latency (ms):                    163876.35 
+---------------Time to First Token----------------
+Mean TTFT (ms):                          74930.30  
+Median TTFT (ms):                        87071.13  
+P90 TTFT (ms):                           87201.04  
+P95 TTFT (ms):                           118429.44 
+P99 TTFT (ms):                           141758.20 
+-----Time per Output Token (excl. 1st token)------
+Mean TPOT (ms):                          48.54     
+Median TPOT (ms):                        43.29     
+P90 TPOT (ms):                           65.78     
+P95 TPOT (ms):                           85.98     
+P99 TPOT (ms):                           94.45     
+---------------Inter-Token Latency----------------
+Mean ITL (ms):                           48.61     
+Median ITL (ms):                         43.07     
+P90 ITL (ms):                            44.03     
+P95 ITL (ms):                            44.30     
+P99 ITL (ms):                            45.35     
+Max ITL (ms):                            28652.24  
+==================================================
diff --git a/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc40.log b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc40.log
new file mode 100644
index 0000000..ab41631
--- /dev/null
+++ b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc40.log
@@ -0,0 +1,56 @@
+/sgl-workspace/sglang/python/sglang/bench_serving.py:13: FutureWarning: `sglang.bench_serving` is deprecated and will be removed in a future release; use `sglang.benchmark.serving` instead (e.g. `python -m sglang.benchmark.serving`).
+  warnings.warn(
+benchmark_args=Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model=None, served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=80, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=40, output_file='/data/hf_models/bs_results/nomtpsweep_cc40.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6540, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+Waiting up to 60s for http://127.0.0.1:30000/v1/models to become ready...
+Server ready in 0.0s.
+Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model='/data/hf_models/GLM-5.3-NVFP4', served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=80, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=40, output_file='/data/hf_models/bs_results/nomtpsweep_cc40.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6540, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+
+#Input tokens: 1310720
+#Output tokens: 40960
+Starting warmup with 1 sequences...
+Warmup completed with 1 sequences. Starting main benchmark run...
+
  0%|          | 0/80 [00:00<?, ?it/s]
  1%|▏         | 1/80 [00:54<1:12:15, 54.87s/it]
 20%|██        | 16/80 [01:48<06:13,  5.84s/it] 
 39%|███▉      | 31/80 [02:43<03:45,  4.60s/it]
 49%|████▉     | 39/80 [02:43<02:11,  3.21s/it]
 56%|█████▋    | 45/80 [03:00<01:52,  3.21s/it]
 57%|█████▊    | 46/80 [03:37<02:30,  4.44s/it]
 76%|███████▋  | 61/80 [04:32<01:17,  4.07s/it]
 95%|█████████▌| 76/80 [05:04<00:13,  3.32s/it]
100%|██████████| 80/80 [05:04<00:00,  3.81s/it]
+
+============ Serving Benchmark Result ============
+Backend:                                 sglang    
+Traffic request rate:                    inf       
+Max request concurrency:                 40        
+Successful requests:                     80        
+Benchmark duration (s):                  304.60    
+Total input tokens:                      1310720   
+Total input text tokens:                 1310720   
+Total generated tokens:                  40960     
+Total generated tokens (retokenized):    40950     
+Request throughput (req/s):              0.26      
+Input token throughput (tok/s):          4303.11   
+Output token throughput (tok/s):         134.47    
+Peak output token throughput (tok/s):    375.00    
+Peak concurrent requests:                55        
+Total token throughput (tok/s):          4437.58   
+Concurrency:                             31.79     
+----------------End-to-End Latency----------------
+Mean E2E Latency (ms):                   121055.83 
+Median E2E Latency (ms):                 109193.09 
+P90 E2E Latency (ms):                    163874.40 
+P95 E2E Latency (ms):                    163882.77 
+P99 E2E Latency (ms):                    163934.61 
+---------------Time to First Token----------------
+Mean TTFT (ms):                          93857.54  
+Median TTFT (ms):                        87217.63  
+P90 TTFT (ms):                           141069.97 
+P95 TTFT (ms):                           141620.33 
+P99 TTFT (ms):                           141666.45 
+-----Time per Output Token (excl. 1st token)------
+Mean TPOT (ms):                          53.23     
+Median TPOT (ms):                        43.46     
+P90 TPOT (ms):                           91.75     
+P95 TPOT (ms):                           95.66     
+P99 TPOT (ms):                           99.92     
+---------------Inter-Token Latency----------------
+Mean ITL (ms):                           53.30     
+Median ITL (ms):                         42.89     
+P90 ITL (ms):                            44.34     
+P95 ITL (ms):                            44.58     
+P99 ITL (ms):                            45.17     
+Max ITL (ms):                            29114.99  
+==================================================
diff --git a/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc64.log b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc64.log
new file mode 100644
index 0000000..a2a5ab0
--- /dev/null
+++ b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc64.log
@@ -0,0 +1,56 @@
+/sgl-workspace/sglang/python/sglang/bench_serving.py:13: FutureWarning: `sglang.bench_serving` is deprecated and will be removed in a future release; use `sglang.benchmark.serving` instead (e.g. `python -m sglang.benchmark.serving`).
+  warnings.warn(
+benchmark_args=Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model=None, served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=128, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=64, output_file='/data/hf_models/bs_results/nomtpsweep_cc64.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6564, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+Waiting up to 60s for http://127.0.0.1:30000/v1/models to become ready...
+Server ready in 0.0s.
+Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model='/data/hf_models/GLM-5.3-NVFP4', served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=128, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=64, output_file='/data/hf_models/bs_results/nomtpsweep_cc64.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6564, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+
+#Input tokens: 2097152
+#Output tokens: 65536
+Starting warmup with 1 sequences...
+Warmup completed with 1 sequences. Starting main benchmark run...
+
  0%|          | 0/128 [00:00<?, ?it/s]
  1%|          | 1/128 [00:54<1:56:06, 54.86s/it]
  7%|▋         | 9/128 [00:55<08:49,  4.45s/it]  
 12%|█▏        | 15/128 [01:10<08:23,  4.45s/it]
 12%|█▎        | 16/128 [01:48<11:27,  6.14s/it]
 19%|█▉        | 24/128 [01:48<05:43,  3.30s/it]
 23%|██▎       | 30/128 [02:00<05:23,  3.30s/it]
 24%|██▍       | 31/128 [02:43<07:58,  4.94s/it]
 30%|███       | 39/128 [02:43<04:35,  3.10s/it]
 35%|███▌      | 45/128 [03:00<04:17,  3.10s/it]
 36%|███▌      | 46/128 [03:38<06:19,  4.63s/it]
 42%|████▏     | 54/128 [03:38<03:46,  3.06s/it]
 47%|████▋     | 60/128 [03:50<03:27,  3.06s/it]
 48%|████▊     | 61/128 [04:32<04:57,  4.44s/it]
 54%|█████▍    | 69/128 [04:32<02:56,  2.99s/it]
 59%|█████▊    | 75/128 [04:50<02:38,  2.99s/it]
 59%|█████▉    | 76/128 [05:26<03:46,  4.36s/it]
 71%|███████   | 91/128 [06:21<02:28,  4.01s/it]
 83%|████████▎ | 106/128 [07:15<01:24,  3.85s/it]
 95%|█████████▍| 121/128 [07:53<00:23,  3.38s/it]
100%|██████████| 128/128 [07:53<00:00,  3.70s/it]
+
+============ Serving Benchmark Result ============
+Backend:                                 sglang    
+Traffic request rate:                    inf       
+Max request concurrency:                 64        
+Successful requests:                     128       
+Benchmark duration (s):                  473.55    
+Total input tokens:                      2097152   
+Total input text tokens:                 2097152   
+Total generated tokens:                  65536     
+Total generated tokens (retokenized):    65509     
+Request throughput (req/s):              0.27      
+Input token throughput (tok/s):          4428.55   
+Output token throughput (tok/s):         138.39    
+Peak output token throughput (tok/s):    368.00    
+Peak concurrent requests:                79        
+Total token throughput (tok/s):          4566.94   
+Concurrency:                             50.54     
+----------------End-to-End Latency----------------
+Mean E2E Latency (ms):                   186979.29 
+Median E2E Latency (ms):                 217737.21 
+P90 E2E Latency (ms):                    271600.25 
+P95 E2E Latency (ms):                    272187.63 
+P99 E2E Latency (ms):                    272559.88 
+---------------Time to First Token----------------
+Mean TTFT (ms):                          161310.10 
+Median TTFT (ms):                        189947.02 
+P90 TTFT (ms):                           225814.00 
+P95 TTFT (ms):                           249709.49 
+P99 TTFT (ms):                           250822.91 
+-----Time per Output Token (excl. 1st token)------
+Mean TPOT (ms):                          50.23     
+Median TPOT (ms):                        42.91     
+P90 TPOT (ms):                           75.43     
+P95 TPOT (ms):                           91.04     
+P99 TPOT (ms):                           98.53     
+---------------Inter-Token Latency----------------
+Mean ITL (ms):                           50.30     
+Median ITL (ms):                         42.86     
+P90 ITL (ms):                            44.64     
+P95 ITL (ms):                            45.12     
+P99 ITL (ms):                            46.02     
+Max ITL (ms):                            28771.25  
+==================================================
diff --git a/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc8.log b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc8.log
new file mode 100644
index 0000000..748ca27
--- /dev/null
+++ b/experiments/pro6000/glm53_ppmtp_r37_verify_graph/results/nomtpsweep_cc8.log
@@ -0,0 +1,56 @@
+/sgl-workspace/sglang/python/sglang/bench_serving.py:13: FutureWarning: `sglang.bench_serving` is deprecated and will be removed in a future release; use `sglang.benchmark.serving` instead (e.g. `python -m sglang.benchmark.serving`).
+  warnings.warn(
+benchmark_args=Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model=None, served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=16, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=8, output_file='/data/hf_models/bs_results/nomtpsweep_cc8.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6508, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+Waiting up to 60s for http://127.0.0.1:30000/v1/models to become ready...
+Server ready in 0.0s.
+Namespace(backend='sglang', base_url=None, host='127.0.0.1', port=30000, ready_check_timeout_sec=60, dataset_name='random-ids', dataset_path='', dataset_offset=0, agentic_max_turns=None, speed_bench_category=None, speed_bench_output_len=512, model='/data/hf_models/GLM-5.3-NVFP4', served_model_name=None, tokenizer='/data/hf_models/GLM-5.3-NVFP4', num_prompts=16, sharegpt_output_len=None, sharegpt_context_len=None, random_input_len=16384, random_output_len=512, random_range_ratio=1.0, image_count=1, image_resolution='1080p', random_image_count=False, image_format='jpeg', image_content='random', request_rate=inf, use_trace_timestamps=False, max_concurrency=8, output_file='/data/hf_models/bs_results/nomtpsweep_cc8.json', output_details=False, print_requests=False, disable_tqdm=False, disable_stream=False, return_logprob=False, top_logprobs_num=0, token_ids_logprob=None, logprob_start_len=-1, return_routed_experts=False, cache_report=False, seed=6508, disable_ignore_eos=False, temperature=0.0, top_p=1.0, extra_request_body=None, apply_chat_template=False, profile=False, plot_throughput=False, profile_activities=['CPU', 'GPU'], profile_start_step=None, profile_steps=None, profile_num_steps=None, profile_by_stage=False, profile_stages=None, profile_output_dir=None, profile_prefix=None, lora_name=None, lora_request_distribution='uniform', lora_zipf_alpha=1.5, prompt_suffix='', pd_separated=False, profile_prefill_url=None, profile_decode_url=None, flush_cache=True, flush_cache_timeout=60.0, warmup_requests=1, tokenize_prompt=False, gsp_num_groups=64, gsp_prompts_per_group=16, gsp_system_prompt_len=2048, gsp_question_len=128, gsp_output_len=256, gsp_range_ratio=1.0, gsp_fast_prepare=False, gsp_send_routing_key=False, gsp_num_turns=1, gsp_ordered=False, gsp_group_distribution='uniform', gsp_zipf_alpha=None, mooncake_slowdown_factor=1.0, mooncake_num_rounds=1, mooncake_workload='conversation', fake_prefill=False, tag=None, header=None)
+
+#Input tokens: 262144
+#Output tokens: 8192
+Starting warmup with 1 sequences...
+Warmup completed with 1 sequences. Starting main benchmark run...
+
  0%|          | 0/16 [00:00<?, ?it/s]
  6%|▋         | 1/16 [00:39<09:59, 39.94s/it]
 56%|█████▋    | 9/16 [01:18<00:53,  7.69s/it]
100%|██████████| 16/16 [01:18<00:00,  4.93s/it]
+
+============ Serving Benchmark Result ============
+Backend:                                 sglang    
+Traffic request rate:                    inf       
+Max request concurrency:                 8         
+Successful requests:                     16        
+Benchmark duration (s):                  78.92     
+Total input tokens:                      262144    
+Total input text tokens:                 262144    
+Total generated tokens:                  8192      
+Total generated tokens (retokenized):    8191      
+Request throughput (req/s):              0.20      
+Input token throughput (tok/s):          3321.83   
+Output token throughput (tok/s):         103.81    
+Peak output token throughput (tok/s):    200.00    
+Peak concurrent requests:                16        
+Total token throughput (tok/s):          3425.63   
+Concurrency:                             7.99      
+----------------End-to-End Latency----------------
+Mean E2E Latency (ms):                   39431.98  
+Median E2E Latency (ms):                 39432.80  
+P90 E2E Latency (ms):                    39938.59  
+P95 E2E Latency (ms):                    39940.22  
+P99 E2E Latency (ms):                    39941.13  
+---------------Time to First Token----------------
+Mean TTFT (ms):                          18179.50  
+Median TTFT (ms):                        18006.12  
+P90 TTFT (ms):                           19473.09  
+P95 TTFT (ms):                           19474.85  
+P99 TTFT (ms):                           19476.29  
+-----Time per Output Token (excl. 1st token)------
+Mean TPOT (ms):                          41.59     
+Median TPOT (ms):                        40.96     
+P90 TPOT (ms):                           44.77     
+P95 TPOT (ms):                           45.94     
+P99 TPOT (ms):                           48.28     
+---------------Inter-Token Latency----------------
+Mean ITL (ms):                           41.65     
+Median ITL (ms):                         40.70     
+P90 ITL (ms):                            41.54     
+P95 ITL (ms):                            41.70     
+P99 ITL (ms):                            42.21     
+Max ITL (ms):                            4036.70   
+==================================================