replaysim/docs/assets/frontier_vllm_alignment/frontier_vllm_alignment.csv

1	run_id	label	tp	request_count	scale_label	scale_value	fixture	kv_blocks	frontier_completed	frontier_total	frontier_complete	vllm_completed	vllm_total	frontier_preemptions	vllm_preemptions	frontier_prefix_hit	vllm_prefix_hit	prefix_hit_delta	frontier_rps	vllm_rps	rps_ratio	frontier_total_tps	vllm_total_tps	total_tps_ratio	frontier_decode_tps	vllm_decode_tps	decode_tps_ratio	frontier_ttft_p50_s	vllm_ttft_p50_s	ttft_p50_ratio	frontier_ttft_p95_s	vllm_ttft_p95_s	ttft_p95_ratio	frontier_tpot_p50_s	vllm_tpot_p50_s	tpot_p50_ratio	frontier_tpot_p95_s	vllm_tpot_p95_s	tpot_p95_ratio	frontier_e2e_p50_s	vllm_e2e_p50_s	e2e_p50_ratio	frontier_e2e_p95_s	vllm_e2e_p95_s	e2e_p95_ratio	notes
2	tp1_n100_scale1	TP1 N100 raw	1	100	raw	1	coder_100	15281	96	100	false	100	100	0	8	0.2487845616	0.2510820686	-0.002297507075	0.4048148795	0.6879880691	0.588403924	2348.908821	3832.320581	0.6129207541	347.7992338	567.4456795	0.6129207541	0.9087481136	4.503025495	0.201808343	12.76295815	29.06046906	0.4391862402	0.05688966428	0.06608134396	0.8609035603	0.1456880793	0.6211491471	0.2345460505	30.93928316	41.84076733	0.7394530534	119.6361376	97.36622969	1.228723121	Frontier incomplete before lifecycle fix; included as TP1 100-request baseline.
3	tp1_n500_scale1	TP1 N500 raw	1	500	raw	1	coder_500	15281	439	500	false	500	500	0	63	0.1192374692	0.3868498695	-0.2676124002	0.660990472	0.8401719451	0.7867323776	4733.748762	5282.903731	0.896050544	656.2204998	732.3476384	0.896050544	136.7755789	185.6581683	0.7367064976	340.2371222	375.8950067	0.9051387119	0.05643274739	0.04975253624	1.134268756	0.08942839773	0.0918798539	0.9733188935	177.7998574	224.2697872	0.7927945162	397.29145	417.3562933	0.9519239469	Frontier incomplete; useful as high-pressure stress signal.
4	tp1_n200_scale0667	TP1 N200 scale 0.667	1	200	0.667	0.6666666667	coder_200_ts0667	15281	176	200	false	200	200	0	26	0.170276008	0.2697549478	-0.09947893984	0.5830903706	0.8236788215	0.7079098737	3913.437526	4864.778909	0.8044430383	593.287826	737.51378	0.8044430383	20.58014532	34.56323652	0.595434554	96.71793818	120.8039818	0.800618794	0.05837096651	0.05145431897	1.13442307	0.235894569	0.2534757496	0.9306395954	73.20731169	83.6219905	0.875455263	189.2402903	183.726977	1.030008186	Dense-arrival run; Frontier incomplete before lifecycle fix.
5	tp1_n200_scale2	TP1 N200 scale 2	1	200	2	2	coder_200_ts2	15281	200	200	true	200	200	33	43	0.23134169	0.2697549478	-0.03841325784	0.5936627655	0.8029813635	0.7393232178	3506.267279	4742.53641	0.7393232178	531.5597036	718.9814831	0.7393232178	9.595321274	9.216767096	1.041072338	77.50341053	69.21141595	1.119806747	0.05421362546	0.04970337519	1.09074334	0.06653162646	0.06863309532	0.9693811149	61.45769412	55.00248734	1.117362088	174.4840836	142.3375087	1.225847531	After Frontier decode-preemption lifecycle fix.
6	tp1_n200_scale3	TP1 N200 scale 3	1	200	3	3	coder_200_ts3	15281	200	200	true	200	200	20	16	0.2176751278	0.2697549478	-0.05207982007	0.5739781652	0.7802265504	0.735655772	3390.00688	4608.142843	0.735655772	513.9343094	698.607051	0.735655772	1.001474116	1.166151478	0.8587856162	45.9466567	32.25842447	1.424330464	0.05339333437	0.04616159714	1.156661331	0.06861254671	0.0713836296	0.9611804148	44.76058145	33.21267588	1.34769573	154.5483135	122.7887113	1.258652459	After Frontier decode-preemption lifecycle fix.
7	tp2_n200_scale2	TP2 N200 scale 2	2	200	2	2	coder_200_ts2	69055	200	200	true	200	200	0	0	0.2697549478	0.2697549478	0	0.7756823572	1.277818683	0.607036325	4581.304111	7547.001591	0.607036325	694.5382258	1144.14607	0.607036325	0.2690959621	0.225119116	1.195349231	6.744624223	0.715071776	9.432094022	0.04295527658	0.03004499679	1.429698158	0.05288764732	0.04340382318	1.218502046	26.05122482	16.44861007	1.583794905	106.7591651	72.5347179	1.471835394	Uses true-mixed TP2/TP4 attention profile.
8	tp2_n200_scale3	TP2 N200 scale 3	2	200	3	3	coder_200_ts3	69055	200	200	true	200	200	0	0	0.2697549478	0.2697549478	0	0.6877705321	1.088050278	0.6321128225	4062.082806	6426.199028	0.6321128225	615.8228567	974.2293382	0.6321128225	0.1341535495	0.153530943	0.8737883511	0.5741378218	0.6270455511	0.9156237864	0.03937896849	0.01905767256	2.06630523	0.04670767225	0.02799082097	1.668678182	21.78596494	9.956003374	2.188223941	101.5918393	53.98348621	1.881905864	Uses true-mixed TP2/TP4 attention profile.
9	tp4_n200_scale2	TP4 N200 scale 2	4	200	2	2	coder_200_ts2	177077	200	200	true	200	200	0	0	0.2697549478	0.2697549478	0	0.8525337931	1.536203537	0.5549614829	5035.200987	9073.063884	0.5549614829	763.350233	1375.501285	0.5549614829	0.09755515041	0.1704972619	0.5721801589	0.3856872342	1.419861408	0.2716372401	0.03366585047	0.01634437735	2.059781767	0.03838265621	0.02831690026	1.355468143	18.65216282	9.260885488	2.014079846	84.93775414	43.62188903	1.947136083	Uses true-mixed TP2/TP4 attention profile.
10	tp4_n200_scale3	TP4 N200 scale 3	4	200	3	3	coder_200_ts3	177077	200	200	true	200	200	0	0	0.2697549478	0.2697549478	0	0.7373665172	1.253504493	0.5882440162	4355.004629	7403.398096	0.5882440162	660.2306059	1122.375388	0.5882440162	0.08859749135	0.100106278	0.885034317	0.3458954617	0.3184188101	1.086290919	0.03106778109	0.009410284212	3.301471071	0.03578285082	0.01279276668	2.79711588	16.90291941	5.54948732	3.045852424	83.00995365	27.86907583	2.978568581	Uses true-mixed TP2/TP4 attention profile.