biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
12,710 Commits 2 Branches 140 Tags
2a42ae790d3f42a381b782a504947255aa0db090
Commit Graph

137 Commits

Author SHA1 Message Date
Matthew Bonanni
d49899732e [Spec Decode][UX] Add acceptance stats to vllm bench serve report (#31739) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
 2026-01-06 21:21:42 +00:00
Elvir Crnčević
dba95378a6 Report error log after vllm bench serve (#31808) 
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
 2026-01-06 20:24:19 +00:00
Reagan Lee
1f5b7c41c3 Add Multimodal Processor Benchmark (#29105) 
Signed-off-by: Reagan Lee <reaganjlee@gmail.com>
Signed-off-by: Reagan <reaganjlee@gmail.com>
 2026-01-01 19:26:53 -08:00
Ning Xie
3b8f31b362 [benchmark] use model card root instead of id (#31329) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2025-12-26 10:55:56 +08:00
Ming Yang
3bb9561928 Revert "[bench] Support common prefix len config (for decode-only bench)" (#31240) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
 2025-12-23 21:17:23 -08:00
zhrrr
eee600c34f [Misc] support nsys profile for bench latency (#29776) 
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
 2025-12-18 14:52:20 +00:00
Michael Goin
519ef9a911 [UX] Make vllm bench serve discover model by default and use --input-len (#30816) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-12-17 01:55:30 -08:00
Junru Shen
676db55eec [Bugfix] Fix prefix_repetition routing in bench throughput (#29663) 
Signed-off-by: Junru Shen <jrshen.sjr@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-16 01:37:15 -08:00
Vensen
add4b0ca44 [Bugfix][benchmarks] Fix input token calculation for rerank benchmark metrics (#30596) 
Signed-off-by: vensen <vensenmu@gmail.com>
 2025-12-14 14:57:15 +00:00
Bin Bao
a8ec486592 [Misc] Add a script to benchmark compilation time (#29919) 
Signed-off-by: Bin Bao <binbao@meta.com>
 2025-12-14 13:02:39 +00:00
Matthew Bonanni
794a7875ee [Misc] Consistent case for vllm bench serve results (#30403) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-12-10 09:44:02 -08:00
Benjamin Chislett
e858bfe051 [Cleanup] Refactor profiling env vars into a CLI config (#29912) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-09 13:29:33 -05:00
Rohan Potdar
40a046cd82 [Bugfix]: Fix TokenizerLike interface (#30009) 
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
 2025-12-05 20:56:40 -08:00
Ming Yang
f16356fe36 [bench] Support common prefix len config (for decode-only bench) (#29934) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
 2025-12-05 10:26:52 +00:00
Copilot
1c593e117d Fix boolean nested params, add dict format support, and enhance plotting for vllm bench sweep (#29025) 
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ProExpertProg <11367180+ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-12-02 20:40:56 +00:00
Cyrus Leung
653591d5e7 [Chore] Move tokenizer initialization methods (#29793) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-02 13:33:37 +08:00
Cyrus Leung
34a984274e [Misc] Refactor tokenizer interface (#29693) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-29 04:02:21 -08:00
rongfu.leng
480598958e [Feature][Bench] Add pareto visualization (#29477) 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
 2025-11-27 23:53:20 -08:00
Didier Durand
66d3d5422c [Doc]: fixing typos in diverse files (#29492) 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
 2025-11-27 07:15:50 -08:00
rongfu.leng
68dfe28eae [Feature][Benchmark] add --link-vars can filter when serve_param equal bench_param (#28909) 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
 2025-11-24 02:02:28 -08:00
scottzh8
3bc1175798 [Bugfix] Fix host and port join for ipv6 in bench serve (#28679) 
Signed-off-by: Scott Zhang <scottzh@fb.com>
Co-authored-by: Scott Zhang <scottzh@fb.com>
 2025-11-16 10:20:57 +00:00
Jialin Ouyang
b30372cbd0 [Perf] Move gc.freeze logic from EngineCoreProc to EngineCore for better coverage (#27896) 
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
 2025-11-10 15:34:18 -08:00
Wentao Ye
4b1ff13221 [Feature] Default ignore_eos True for random dataset (#28227) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-11-07 07:35:33 -05:00
汪志鹏
315068eb4a [FixBug]Aeala/ShareGPT_Vicuna_unfiltered marked as multimodal benchmark (#28265) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2025-11-07 09:35:22 +00:00
Jacob Zhong
d72299d47b Make the cv2 dependency optional (#27780) 
Signed-off-by: Jacob <cmpute@qq.com>
 2025-11-06 05:08:55 +00:00
Sophie du Couédic
a4398fbb5e [Feature][Benchmarks] Support inf burstiness (#26941) 
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
 2025-11-03 18:33:17 +00:00
Seiji Eicher
b2e65cb4a7 [benchmark] Make request IDs unique across clients by default (#27723) 
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
 2025-10-30 17:40:35 -07:00
Cyrus Leung
ecca3fee76 [Frontend] Add vllm bench sweep to CLI (#27639) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-29 05:59:48 -07:00
Eugene Khvedchenya
5e72216d17 Feature/video support in random mm dataset (#25963) 
Signed-off-by: Eugene Khvedchenia <ekhvedchenia@nvidia.com>
Signed-off-by: Eugene Khvedchenya <ekhvedchenia@nvidia.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-10-29 18:24:52 +08:00
Yeshwanth N
71b1c8b667 [Chore]:Extract math and argparse utilities to separate modules (#27188) 
Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>
 2025-10-26 04:03:32 -07:00
Lucia Fang
315b860abe [bugfix]fix empty prompts for async-engine mode in benchmark throughput (#27494) 
Signed-off-by: Lucia Fang <fanglu@fb.com>
 2025-10-26 08:16:35 +00:00
Cyrus Leung
b7030d962b [Benchmark] Enable benchmark to run with encoding_format="bytes" (#27467) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-24 11:16:50 +00:00
Cyrus Leung
6738e4a093 [Bugfix] Fix SLA tuner initialization (#27355) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-22 20:43:04 -07:00
Cyrus Leung
ceacedc1f9 [Benchmark] Add plot utility for parameter sweep (#27168) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-21 20:30:03 -07:00
Cyrus Leung
d31f7844f8 [Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-19 05:20:55 -07:00
Cyrus Leung
b3aba04e5a [Benchmark] Convenience script for multiple parameter combinations (#27085) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-18 23:57:01 -07:00
Harry Mellor
6c9fdbf725 [Docs] Replace rst style double-backtick with md single-backtick (#27091) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-17 02:47:34 -07:00
Tomas Ruiz
965c5f4914 vllm bench serve shows num of failed requests (#26478) 
Signed-off-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
 2025-10-16 19:55:09 -07:00
Cyrus Leung
4d4d6bad19 [Chore] Separate out vllm.utils.importlib (#27022) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-17 00:48:59 +00:00
Wentao Ye
23583ee28c [Bug] Add Assertion for random-input-len / random-output-len (#26834) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-16 21:36:39 +00:00
kimbochen
013abde6ef Adding Warmup to Benchmark Serving (#26943) 
Signed-off-by: Kimbo Chen <chentenghung@gmail.com>
 2025-10-16 12:44:32 -07:00
Cyrus Leung
334535b6fb [Benchmark] Show E2EL by default for pooling models (#27014) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-16 12:47:09 +00:00
Cyrus Leung
17838e50ef [Benchmark] Use truncation by default for pooling benchmarks (#26992) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-16 16:02:39 +08:00
Cyrus Leung
f6cdc9a02f [Chore] Rename utils submodules (#26920) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-16 03:58:13 +00:00
Cyrus Leung
828523ad8e [Chore] Separate out vllm.utils.async_utils (#26913) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-15 15:33:00 +00:00
wangxiyuan
8f4b313c37 [Misc] rename torch_dtype to dtype (#26695) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-10-15 12:11:48 +00:00
rongfu.leng
a27b288e4a [Feature] default --extra-body param to disable thinking in vllm bench serve (#26784) 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
 2025-10-15 04:23:44 +00:00
kourosh hakhamaneshi
a2986b3e33 [Bugfix] Fixes prefix-repetition benchmark script (#26828) 
Signed-off-by: Kourosh Hakhamaneshi <Kourosh@anyscale.com>
 2025-10-15 02:54:43 +00:00
Maximilien de Bayser
fe3edb4cf0 Add support for the /rerank endpoint in vllm bench serve (#26602) 
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
 2025-10-14 04:25:43 +00:00
Harry Mellor
8fcaaf6a16 Update Optional[x] -> x | None and Union[x, y] to x | y (#26633) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-12 09:51:31 -07:00