Logo
Explore Help
Sign In
xinyun/vllm
1
0
Fork 0
You've already forked vllm
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-31 10:37:03 +08:00
Code Issues Packages Projects Releases Wiki Activity
vllm/tests/kernels/attention
History
RUTHLESS-BOT 53c730286c
[Misc] parametrize 'dtype' in test_flash_mla (#22641)
Signed-off-by: RUTHLESS-BOT <wujiafeng@cmbchina.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-08-12 16:31:48 -04:00
..
conftest.py
…
test_aiter_flash_attn.py
[ROCm][AITER] Enable fp8 kv cache on rocm aiter backend. (#20295)
2025-07-25 06:50:21 -07:00
test_attention_selector.py
[UX] Fail if an invalid attention backend is specified (#22217)
2025-08-04 23:54:52 -07:00
test_attention.py
…
test_cache.py
…
test_cascade_flash_attn.py
…
test_encoder_decoder_attn.py
…
test_flash_attn.py
…
test_flashinfer_trtllm_attention.py
[NVIDIA] Support Flashinfer TRT-LLM Prefill Attention Kernel (#22095)
2025-08-05 02:45:34 -07:00
test_flashinfer.py
[Misc] Add sliding window to flashinfer test (#21282)
2025-07-21 08:37:49 -07:00
test_flashmla.py
[Misc] parametrize 'dtype' in test_flash_mla (#22641)
2025-08-12 16:31:48 -04:00
test_lightning_attn.py
…
test_merge_attn_states.py
…
test_mha_attn.py
…
test_mla_decode_cpu.py
…
test_prefix_prefill.py
…
test_rocm_attention_selector.py
…
test_triton_decode_attention.py
…
test_triton_unified_attention.py
…
Powered by Gitea Version: 1.23.1 Page: 7582ms Template: 5ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API