Yongfei Xuandybyang d2b8c4123e Opt fused triton moe: add tma for down proj kernel (#10567) ...

Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>

2025-10-28 14:26:17 +08:00

..

bench_attention_sink

…

bench_in_batch_prefix

…

benchmark_batch

…

benchmark_vllm_060

…

blog_v0_2

…

boolq

…

ceval

…

deepseek_v3

[doc] add example of using w4fp8 for Deepseek (#12057)

2025-10-26 20:10:38 -07:00

dspy

…

generative_agents

…

gpt_oss

…

gsm8k

…

hellaswag

…

hf3fs

…

hicache

Revert "lang: support direct video inference" (#12038)

2025-10-23 19:21:31 -07:00

json_decode_regex

…

json_jump_forward

…

json_schema

Tiny move files to utils folder (#11166)

2025-10-03 22:40:06 +08:00

kernels

Opt fused triton moe: add tma for down proj kernel (#10567)

2025-10-28 14:26:17 +08:00

line_retrieval

…

llava_bench

…

llm_judge

…

long_json_decode

…

lora

Add env var to control custom Triton kernel cache and set CSGMV as default backend. (#12176)

2025-10-27 17:49:32 -07:00

mmlu

…

mmmu

vlm: enforce pybase64 for image and str encode/decode (#10700)

2025-10-21 19:05:32 +08:00

mtbench

…

multi_chain_reasoning

…

multi_document_qa

…

multi_turn_chat

Tiny move files to utils folder (#11166)

2025-10-03 22:40:06 +08:00

prefill_only

Add support for Matryoshka embeddings (#126) (#11142)

2025-10-28 02:49:36 +08:00

react

…

reasoning_benchmark

…

tip_suggestion

…

tree_of_thought_deep

…

tree_of_thought_v0

…