Yuan Luo cb3918a091 Optimize moe_sum_reduce_kernel (#9477) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>

2025-09-07 09:16:18 +08:00

..

bench_attention_sink

bench: add attention sink op benchmark, triton and trtllm-gen [B200] (#8932)

2025-08-08 00:16:23 -07:00

bench_in_batch_prefix

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

benchmark_batch

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

benchmark_vllm_060

Revert "fix some typos" (#6244)

2025-05-12 12:53:26 -07:00

blog_v0_2

Add a new api configure_logging to allow dumping the requests (#2875)

2025-01-13 14:24:00 -08:00

boolq

[benchmark] Add benchmark scripts for ceval and boolq (#8946)

2025-08-23 15:40:15 +08:00

ceval

[benchmark] Add benchmark scripts for ceval and boolq (#8946)

2025-08-23 15:40:15 +08:00

deepseek_v3

chore: bump v0.5.2rc2 (#10050)

2025-09-04 20:07:27 -07:00

dspy

Organize Benchmark (#381)

2024-05-05 16:14:17 +08:00

generative_agents

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

gpt_oss

[Fix] Add speculative_draft_model_revision to server_args (#5255)

2025-09-05 19:45:46 +08:00

gsm8k

Simplify frontend language (#9029)

2025-08-10 10:59:30 -07:00

hellaswag

Simplify frontend language (#9029)

2025-08-10 10:59:30 -07:00

hf3fs

refactor(hicache): Introduce generic HiCacheStorageConfig for improved configuration management (#9555)

2025-08-26 17:55:20 -07:00

hicache

Add lora_path argument to bench_multiturn.py (#10092)

2025-09-05 19:20:42 -07:00

json_decode_regex

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

json_jump_forward

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

json_schema

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

kernels

Optimize moe_sum_reduce_kernel (#9477)

2025-09-07 09:16:18 +08:00

line_retrieval

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

llava_bench

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

llm_judge

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

long_json_decode

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

lora

support 1 shot allreduce in 1-node and 2-node using mscclpp (#6277)

2025-06-04 22:11:24 -07:00

mmlu

Minor tool for comparison of benchmark results (#7974)

2025-07-27 00:27:50 -07:00

mmmu

[GLM4.1V and GLM4.5V] Add vision transformer num_dummy_head support: max tp=4 -> max tp=8 (#9059)

2025-08-18 14:40:13 -07:00

mtbench

[Fix] Add speculative_draft_model_revision to server_args (#5255)

2025-09-05 19:45:46 +08:00

multi_chain_reasoning

Revert "fix some typos" (#6244)

2025-05-12 12:53:26 -07:00

multi_document_qa

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

multi_turn_chat

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

react

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

reasoning_benchmark

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

score

[Generative Score API] Optimization to Remove Decode. (#8840)

2025-08-14 05:12:24 +08:00

tip_suggestion

Replace time.time() to time.perf_counter() for benchmarking. (#6178)

2025-05-11 14:32:49 -07:00

tree_of_thought_deep

Revert "fix some typos" (#6244)

2025-05-12 12:53:26 -07:00

tree_of_thought_v0

Revert "fix some typos" (#6244)

2025-05-12 12:53:26 -07:00