cs-cat 22e378af86 Fix result writer in tuning_block_wise_kernel.py, and add FP8 kernel config for L40 (#20368) ...

Signed-off-by: cs-cat <118669451+cs-cat@users.noreply.github.com>

2026-03-20 09:28:54 +08:00

..

asr

Whisper model support & /v1/audio/transcriptions endpoint & benchmark (#16983)

2026-02-23 17:28:37 -08:00

bench_attention_sink

…

bench_in_batch_prefix

…

bench_linear_attention

[GDN] Support GDN packed decode (#20627)

2026-03-18 13:20:07 +08:00

bench_rope

…

benchmark_batch

…

benchmark_vllm_060

…

blog_v0_2

…

boolq

…

ceval

…

deepseek_v3

[Doc] Update version references and add automation (#18409)

2026-03-04 09:51:46 -08:00

dspy

…

fla

…

generative_agents

…

gpt_oss

…

gsm8k

…

hellaswag

…

hf3fs

…

hicache

Enhance bench_multiturn.py with OpenAI API support and richer metrics (#19724)

2026-03-03 13:48:04 -08:00

json_decode_regex

…

json_jump_forward

…

json_schema

…

kernels

Fix result writer in tuning_block_wise_kernel.py, and add FP8 kernel config for L40 (#20368)

2026-03-20 09:28:54 +08:00

line_retrieval

…

llava_bench

…

llm_judge

…

long_json_decode

…

lora

[Refactor] Benchmark: Add typed DatasetArgs/Loader registry and CPU dataset unit tests (#19147)

2026-02-24 12:22:01 -08:00

mmlu

…

mmmu

Add Mistral Small 4 (Pixtral) support (#20708)

2026-03-18 14:15:32 -07:00

mtbench

…

multi_chain_reasoning

…

multi_document_qa

…

multi_turn_chat

…

prefill_only

…

react

…

reasoning_benchmark

…

tip_suggestion

…

tree_of_thought_deep

…

tree_of_thought_v0

…