[trillium.rs] update dependencies

[jbr]

Description

Updates some trillium dependencies that may have performance impacts (alloc counts).

---

PR Commands — comment on this PR to trigger (requires collaborator approval):

Command	Description
/benchmark -f <framework>	Run every test the framework subscribes to
/benchmark -f <framework> -t <test>	Run one test only
/benchmark -f <framework> --save	Run and save results (updates the leaderboard on merge)
/benchmark -f <framework> -t <test> --save	Run one test and save results
/benchmark -f <framework> --compare <other>	Measure the deltas against another framework instead of this one
/benchmark-multiple -f <fw1>,<fw2>,...	Benchmark several frameworks in one run — takes -t and --save too; saved results land in a single commit
/benchmark-multiple --save	No -f needed: benchmark and save every framework the PR touches
/benchmark-test -t <test>	Benchmark all enabled frameworks subscribed to <test> and save the results

For /benchmark, always specify -f <framework>; the flags combine in any order. Results come back as a comment with a per-profile table of RPS, p99, CPU and memory — one table per framework on multi runs. A new benchmark comment while a run is in flight queues behind it (one deep) instead of cancelling it. For multi-framework PRs (dependency bumps, same-language refactors) prefer /benchmark-multiple, which runs everything in a single job and commits all saved results together, so no run overwrites another. --compare works on single-framework runs only.

What the deltas are measured against. By default, this framework's own results published on main - answering "did this change help?". When you are tuning a variant or a successor entry, --compare re-bases them on another entry instead:

/benchmark -f genhttp --compare genhttp-kestrel

The reply states which baseline it used, and profiles the other framework does not run show n/a rather than a delta.

---

Run benchmarks locally

You can validate and benchmark your framework locally with the lite script — no CPU pinning, fixed connection counts, all load generators run in Docker.

./scripts/validate.sh <framework>
./scripts/benchmark-lite.sh <framework> baseline
./scripts/benchmark-lite.sh --load-threads 4 <framework>

Requirements: Docker Engine on Linux. Load generators (gcannon, h2load, h2load-h3, wrk) are built as self-contained Docker images on first run.

[jbr]

/benchmark-multiple --save

[github-actions]

👋 Benchmark request received. A collaborator will review and approve the run.

[github-actions]

Benchmark Results

Frameworks: 2 | Test: all tests

✅ trillium

Test	Conn	RPS	Rate	CPU/req	p99	p99.9	CPU	Mem	Δ RPS	Δ Mem
baseline	4096	596,428	—	—	—	—	6042.1%	208MiB	-0.3%	+4.0%
pipelined	4096	2,942,210	—	—	—	—	6337.3%	225MiB	-0.9%	+21.0%
limited-conn	4096	511,540	—	—	—	—	2397.7%	219MiB	+2.7%	+5.3%
json-comp	4096	112,571	—	—	—	—	6247.4%	762MiB	-3.2%	-1.7%
json-comp	16384	110,848	—	—	—	—	6011.9%	774MiB	-1.8%	+2.9%
json-tls	4096	613,708	—	—	—	—	6468.7%	418MiB	+2.7%	-2.3%
8gbit	512	48,662	0.9732 ⚠️	50.22us	149.0us	4362.0us	242.5%	228MiB	-0.9%	-5.0%
static-tls	1024	541,037	—	—	—	—	6401.1%	514MiB	-2.4%	-2.8%
async-db	1024	214,163	—	—	—	—	3256.4%	241MiB	+1.5%	+1.3%
fortunes	1024	207,201	—	—	—	—	5009.9%	319MiB	+4.2%	+0.3%
baseline-h2	256	1,113,605	—	—	—	—	5457.2%	950MiB	-2.0%	+8.4%
baseline-h2	1024	1,242,176	—	—	—	—	5325.8%	3.8GiB	+9.7%	+35.7%
static-h2	256	20,151	—	—	—	—	4108.2%	1.8GiB	-7.0%	-5.3%
static-h2	1024	18,419	—	—	—	—	3762.7%	2.5GiB	~0%	-16.7%
baseline-h2c	256	1,281,402	—	—	—	—	5258.6%	897MiB	+10.3%	+6.2%
baseline-h2c	1024	1,151,879	—	—	—	—	5493.4%	3.1GiB	-9.7%	+34.8%
baseline-h2c	4096	1,237,468	—	—	—	—	5530.5%	9.6GiB	+10.4%	+47.7%
json-h2c	1024	955,862	—	—	—	—	5717.6%	1.9GiB	-2.5%	+26.7%
json-h2c	4096	928,509	—	—	—	—	5668.6%	4.9GiB	+2.6%	-3.9%
baseline-h3	64	425,126	—	—	—	—	2539.1%	301MiB	+1.3%	+3.8%
static-h3	64	219,349	—	—	—	—	2439.4%	507MiB	+3.3%	-17.7%
gateway-64	512	81,132	—	—	—	—	5405.6%	3.0GiB	-1.2%	+3.4%
gateway-64	1024	75,235	—	—	—	—	5125.8%	5.8GiB	-2.6%	+9.4%
gateway-h3	64	82,606	—	—	—	—	4092.8%	896MiB	-1.0%	-1.9%
gateway-h3	256	60,594	—	—	—	—	2788.9%	1.9GiB	-1.8%	-20.8%
unary-grpc	256	690,051	—	—	—	—	5421.3%	467MiB	-7.2%	+6.9%
unary-grpc	1024	709,412	—	—	—	—	5595.0%	1.4GiB	+1.4%	+7.7%
unary-grpc-tls	256	760,673	—	—	—	—	5288.4%	440MiB	+4.9%	+3.8%
unary-grpc-tls	1024	650,980	—	—	—	—	5682.8%	1.4GiB	+1.0%	~0%
echo-ws	512	440,297	—	—	—	—	3279.7%	306MiB	-0.3%	-7.0%
echo-ws	4096	355,252	—	—	—	—	3987.8%	602MiB	+0.4%	+5.4%
echo-ws	16384	342,662	—	—	—	—	3660.7%	1.8GiB	-2.1%	+152.8%
echo-ws-pipeline	512	9,127,299	—	—	—	—	3753.9%	292MiB	~0%	-16.6%
echo-ws-pipeline	4096	7,857,900	—	—	—	—	4070.6%	659MiB	-0.6%	-4.2%
echo-ws-pipeline	16384	6,786,700	—	—	—	—	3387.4%	1.3GiB	-9.2%	+35.4%
echo-ws-limited	512	270,939	—	—	—	—	2913.4%	471MiB	+0.4%	-1.1%
echo-ws-limited	4096	272,378	—	—	—	—	2821.0%	461MiB	~0%	-14.9%
latency-1m	1024	632,675	0.6327 ⚠️	96.22us	7055360.0us	7182336.0us	6343.3%	159MiB	+7.2%	+15.2%
latency-10k	1024	9,912	0.9912	27.16us	107.0us	612.0us	25.0%	159MiB	-0.2%	+4.6%
latency-500k-8cpu	1024	281,645	0.5633 ⚠️	28.05us	7960576.0us	8169472.0us	772.3%	73MiB	-3.4%	-6.4%
async	32000	407,249	—	—	—	—	3325.1%	1.5GiB	-3.0%	+7.1%

✅ trillium-tuned

Test	Conn	RPS	Rate	CPU/req	p99	p99.9	CPU	Mem	Δ RPS	Δ Mem
baseline	4096	574,772	—	—	—	—	6310.2%	417MiB	-11.1%	+2.0%
pipelined	4096	2,797,935	—	—	—	—	6396.3%	365MiB	-2.3%	+18.9%
limited-conn	4096	514,442	—	—	—	—	5959.0%	495MiB	-9.4%	-1.2%
json-comp	4096	110,562	—	—	—	—	6253.1%	1.0GiB	+0.3%	+2.1%
json-comp	16384	99,874	—	—	—	—	6433.0%	1.4GiB	+0.6%	-6.7%
json-tls	4096	526,770	—	—	—	—	6249.0%	503MiB	-3.0%	+4.1%
8gbit	512	49,155	0.9831	54.28us	130.0us	1354.0us	247.1%	270MiB	-0.4%	-2.5%
static-tls	1024	490,320	—	—	—	—	6380.1%	912MiB	-13.6%	-19.0%
async-db	1024	229,592	—	—	—	—	3557.5%	256MiB	+1.8%	-7.9%
fortunes	1024	159,782	—	—	—	—	4420.5%	375MiB	+2.3%	-0.5%
baseline-h2	256	1,244,433	—	—	—	—	5454.5%	770MiB	-8.8%	-1.8%
baseline-h2	1024	1,254,584	—	—	—	—	5748.0%	2.6GiB	+2.0%	+13.0%
static-h2	256	190,910	—	—	—	—	6199.4%	11.1GiB	+0.8%	+6.7%
static-h2	1024	179,689	—	—	—	—	6148.9%	15.4GiB	+0.5%	-4.3%
baseline-h2c	256	1,381,238	—	—	—	—	5407.8%	836MiB	+0.2%	+13.1%
baseline-h2c	1024	1,414,848	—	—	—	—	5669.5%	2.9GiB	+14.3%	+16.0%
baseline-h2c	4096	1,343,323	—	—	—	—	5256.3%	10.1GiB	+0.9%	+11.0%
json-h2c	1024	1,179,716	—	—	—	—	5540.8%	1.3GiB	+0.1%	-7.1%
json-h2c	4096	1,059,700	—	—	—	—	5858.0%	4.6GiB	+0.9%	+4.5%
baseline-h3	64	427,713	—	—	—	—	2596.2%	416MiB	-2.6%	+8.1%
static-h3	64	226,765	—	—	—	—	2574.6%	701MiB	-2.9%	-1.1%
gateway-64	512	76,041	—	—	—	—	5713.4%	2.8GiB	+3.8%	-6.7%
gateway-64	1024	68,759	—	—	—	—	5308.3%	5.5GiB	-7.2%	-1.8%
gateway-h3	64	82,375	—	—	—	—	4075.8%	917MiB	-0.2%	-1.6%
gateway-h3	256	60,216	—	—	—	—	2921.6%	2.4GiB	-7.5%	+118.2%
unary-grpc	256	664,634	—	—	—	—	5385.9%	695MiB	-6.8%	-8.4%
unary-grpc	1024	652,387	—	—	—	—	5703.7%	2.2GiB	-10.9%	~0%
unary-grpc-tls	256	784,140	—	—	—	—	5448.0%	935MiB	-2.7%	+34.9%
unary-grpc-tls	1024	796,764	—	—	—	—	5787.1%	2.6GiB	+1.5%	+36.8%
echo-ws	512	1,692,428	—	—	—	—	6529.4%	351MiB	+2.2%	+2.3%
echo-ws	4096	425,623	—	—	—	—	6516.5%	868MiB	+0.2%	-8.8%
echo-ws	16384	406,003	—	—	—	—	6201.0%	3.0GiB	-0.2%	~0%
echo-ws-pipeline	512	15,414,595	—	—	—	—	6683.9%	325MiB	+1.4%	-4.4%
echo-ws-pipeline	4096	10,954,723	—	—	—	—	6591.2%	908MiB	-1.1%	-1.7%
echo-ws-pipeline	16384	6,918,067	—	—	—	—	6209.8%	2.9GiB	-0.1%	-6.5%
echo-ws-limited	512	1,072,355	—	—	—	—	5302.1%	482MiB	+3.6%	-11.7%
echo-ws-limited	4096	533,162	—	—	—	—	5562.6%	1.0GiB	+2.2%	-9.1%
latency-1m	1024	639,132	0.6391 ⚠️	93.01us	9687040.0us	11448320.0us	6185.3%	193MiB	+11.0%	-1.5%
latency-10k	1024	9,983	0.9983	33.40us	118.0us	163.0us	32.3%	192MiB	~0%	-4.5%
latency-500k-8cpu	1024	276,261	0.5525 ⚠️	28.86us	9367552.0us	9629696.0us	764.3%	111MiB	-2.6%	+26.1%
async	32000	594,863	—	—	—	—	6064.1%	1.4GiB	-4.9%	-12.5%