xiegegege 209e5cf7f4 [CE]add 21b mooncake yaml (#7033) ...

* [CE]add 21b cpu cache ,glm mtp,glm for rl config

* [CE]add 21b tp2 yaml

* [CE]add 21b mooncake yaml

* add fastdeploy benchmark,paddletest-155

* [CE] adjust vl wint4 config

* [CE]add glm mtp with updatemodel config

* [CE]fix

* fix

* test

* test

* test

---------

Co-authored-by: xiegegege <>

2026-03-26 20:01:05 +08:00

..

request_yaml

[Benchmark] Update Qwen3 vl 32k yaml (#6946)

2026-03-20 11:48:53 +08:00

deepseek-32k-tp8-wint4.yaml

[Doc]fix deepseek ce (#4560)

2025-10-23 14:09:11 +08:00

eb45-8k-fp8-tp1-dp8_ep.yaml

Create eb45-8k-fp8-tp1-dp8_ep.yaml (#3485)

2025-08-20 14:33:54 +08:00

eb45-21b-a3b-32k-bf16-tp2-mooncake.yaml

[CE]add 21b mooncake yaml (#7033)

2026-03-26 20:01:05 +08:00

eb45-21b-a3b-32k-bf16.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-21b-a3b-32k-wint4-a10.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-21b-a3b-32k-wint4.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-21b-a3b-32k-wint8-cpu-cache.yaml

[CE]add 21b cpu cache ,glm mtp,glm for rl config (#6328)

2026-02-03 20:10:47 +08:00

eb45-21b-a3b-32k-wint8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-21B-vl-128k-wint4-h800-tp1.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

eb45-32k-bf16-a30-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-blockwise-fp8-h800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-tensorwise-fp8-h800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-w4a8c8-a800-tp4.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-w4a8c8-tp4_decode.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

eb45-32k-w4a8c8-tp4_prefill.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

eb45-32k-wint2-h20-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-wint2-tp4.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-32k-wint4-a800-tp4-cinn.yaml

[Doc]add text/vl cinn ce config (#5532)

2025-12-12 16:16:06 +08:00

eb45-32k-wint4-a800-tp4.yaml

[Executor] Default use CUDAGraph (#3594)

2025-10-21 14:25:45 +08:00

eb45-32k-wint4-ep4-tp4.yaml

[CE]add pd router and wint4 tp4 config (#5554)

2025-12-15 15:25:14 +08:00

eb45-32k-wint4-h800-dp8_decode.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-wint4-h800-dp8_prefill.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

eb45-32k-wint4-mtp-h800-tp4.yaml

[benchmark]add qwen3-235b pd+ep yaml (#5225)

2025-11-25 19:53:30 +08:00

eb45-32k-wint4-mtp-tp4-decode.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

eb45-32k-wint4-mtp-tp4-prefill.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

eb45-32k-wint4-p800-tp4.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-wint4-p800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-wint4-prefixcache-a800-tp4.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-wint4-tp1-dp4_ep.yaml

[CE]change yaml name

2025-12-04 19:14:11 +08:00

eb45-32k-wint4-tp4_decode_router.yaml

[CE]add pd router and wint4 tp4 config (#5554)

2025-12-15 15:25:14 +08:00

eb45-32k-wint4-tp4_decode.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-32k-wint4-tp4_prefill_router.yaml

[CE]add pd router and wint4 tp4 config (#5554)

2025-12-15 15:25:14 +08:00

eb45-32k-wint4-tp4_prefill.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-32k-wint8-a800-tp8.yaml

[Executor] Default use CUDAGraph (#3594)

2025-10-21 14:25:45 +08:00

eb45-32k-wint8-p800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-32k-wint8-prefixcache-a800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-128k-wint4-a800-tp8.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-128k-wint4-p800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-128k-wint4-tp1-plas.yaml

[Doc]add plas attention config (#4128)

2025-09-16 15:55:12 +08:00

eb45-128k-wint8-a800-tp8.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-vl-28b-thinking-32k-wint8.yaml

[Docs] add ebvlthinking yaml (#5120)

2025-11-19 15:27:46 +08:00

eb45-vl-28b-thinking-128k-wint8.yaml

[Docs] add ebvlthinking yaml (#5120)

2025-11-19 15:27:46 +08:00

eb45-vl-32k-wint4-a800-tp8-cinn.yaml

[Doc]add text/vl cinn ce config (#5532)

2025-12-12 16:16:06 +08:00

eb45-vl-32k-wint4-a800-tp8.yaml

[CE]add 21b mooncake yaml (#7033)

2026-03-26 20:01:05 +08:00

eb45-vl-32k-wint4-h800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-vl-32k-wint4-tp4.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-vl-32k-wint8-a800-tp8.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-vl-32k-wint8-h800-tp8.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-vl-32k-wint8-tp4.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

eb45-vl-128k-wint4-h800-tp8.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-vl-lite-32k-bf16-a800-tp1.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-vl-lite-32k-wint4-a800-tp1.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45-vl-lite-32k-wint8-a800-tp1.yaml

[benchmark]add lite-vl and x1 yaml (#4130)

2025-09-16 16:38:36 +08:00

eb45t_0dot3b-32k-bf16-a30-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

eb45t_0dot3b-32k-bf16-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

eb45t_0dot3b-32k-wint8-a30-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

eb45t_0dot3b-32k-wint8-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

eb45t_21b-32k-bf16-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

eb45t_21b-32k-wint4-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

eb45t_300b-32k-wint4-h800-tp4-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

GLM45-air-32k-bf16-mtp-updatemodel.yaml

[CE]add 21b mooncake yaml (#7033)

2026-03-26 20:01:05 +08:00

GLM45-air-32k-bf16-mtp.yaml

[CE]add 21b cpu cache ,glm mtp,glm for rl config (#6328)

2026-02-03 20:10:47 +08:00

GLM45-air-32k-bf16-rl.yaml

[CE]add 21b cpu cache ,glm mtp,glm for rl config (#6328)

2026-02-03 20:10:47 +08:00

GLM45-air-32k-bf16.yaml

add glm benchmark yaml (#4289)

2025-09-26 14:23:29 +08:00

GLM45-air-32k-wfp8afp8.yaml

add glm benchmark yaml (#4289)

2025-09-26 14:23:29 +08:00

paddleocr-vl-16k-bf16.yaml

[CE]add paddleocr config yaml (#6097)

2026-01-19 20:07:42 +08:00

qwen2_7b-32k-bf16-a30-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen2_7b-32k-bf16-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen2_7b-32k-bf16-h800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen2_7b-32k-fp8-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen2_7b-32k-fp8-h800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen2_7b-32k-wint8-h800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3_0dot6b-32k-bf16-a30-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen3_0dot6b-32k-bf16-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen3_0dot6b-32k-wint8-a30-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen3_0dot6b-32k-wint8-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen3_30b-32k-bf16-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen3_30b-32k-wint4-h800-tp1-static.yaml

[Executor] CUDA Graph support padding batch (#2844)

2025-07-15 19:49:01 -07:00

qwen3-235b-32k-fp8-tp1-dp4_decode.yaml

[benchmark]add qwen3-235b pd+ep yaml (#5225)

2025-11-25 19:53:30 +08:00

qwen3-235b-32k-fp8-tp1-dp4_prefill.yaml

[benchmark]add qwen3-235b pd+ep yaml (#5225)

2025-11-25 19:53:30 +08:00

qwen3-vl-64k-bf16-tp1.yaml

[Benchmark] Update Qwen3 vl dense yaml (#6945)

2026-03-20 11:26:47 +08:00

qwen3-vl-64k-bf16-tp2.yaml

[Benchmark] Update Qwen3 vl dense yaml (#6945)

2026-03-20 11:26:47 +08:00

qwen3dot6b-32k-bf16-a30-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3dot6b-32k-bf16-a800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3dot6b-32k-bf16-h800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3dot6b-32k-wint8-a30-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3dot6b-32k-wint8-a800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3dot6b-32k-wint8-h800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3moe30b-32k-bf16-a800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3moe30b-32k-bf16-h800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3moe30b-32k-wint4-a800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3moe30b-32k-wint4-h800-tp1.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

qwen3moe235b-32k-wint4-h800-tp4.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

qwen3moe235b-32k-wint8-h800-tp4.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

qwen25_7b-vl-32k-bf16.yaml

[Feature] [PD] add simple router and refine splitwise deployment (#4709)

2025-11-06 14:56:02 +08:00

x1-32k-wint4-h800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

x1-32k-wint4-p800-tp4.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

x1-32k-wint4-p800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

x1-32k-wint4-prefixcache-h800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

x1-32k-wint8-h800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

x1-32k-wint8-p800-tp4.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

x1-32k-wint8-p800-tp8.yaml

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

x1-32k-wint8-prefixcache-h800-tp8.yaml

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

x1-64k-w4a8c8-tp4.yaml

[Feature] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668)

2025-10-31 10:45:27 +08:00

x1-a3b-128k-wint8-h800-tp1.yaml

[Feature] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668)

2025-10-31 10:45:27 +08:00