Skip to content

Issues: flashinfer-ai/flashinfer

Beta
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

112 Open 174 Closed
112 Open 174 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Typo in the Paper
#1098 opened May 29, 2025 by kingzevin
How to combine API and implement same function of 'torch.nn.functional.scaled_dot_product_attention'
#1095 opened May 27, 2025 by alao556
Question about smem descriptor in wgmma
#1078 opened May 21, 2025 by botbw
test_sampling.cu is not updated to the newer sampling kernel interface
#1074 opened May 20, 2025 by 842974287
@yzh119
FA3 FP8 KV8 missing configuration for Llama 1B head dims
#1068 opened May 19, 2025 by nandor
1
AOT Refactor
#1064 opened May 19, 2025 by abcdabcd987
9 of 10 tasks
@abcdabcd987
3
C++ test example failed for test_single_prefill bug Something isn't working
#1057 opened May 14, 2025 by swmobile
@yzh119
3
Build fail because of "unknown" in metadata while installation
#1053 opened May 11, 2025 by IzhanVarsky
3
[BUG] Support 32 head size for SGLang
#1048 opened May 7, 2025 by DavidBao03
@yzh119
Prefill output corrupted by unrelated previous operations, "Barrier error detected. Missing wait" sanitizer error
#1046 opened May 1, 2025 by danieldjohnson
@yzh119
3
Problem when using attention variant with custom mask
#1044 opened Apr 29, 2025 by xiaozxiong
@yzh119
Does flashinfer support head_size = 576 for Ampere GPUs?
#1043 opened Apr 28, 2025 by ghostplant
3
flashinfer.jit: Loading JIT ops: batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False
#1038 opened Apr 24, 2025 by yawnzh
2
Which one of FlashMLA is faster on Hopper?
#1037 opened Apr 24, 2025 by ghostplant
Can flashinfer's CutlassSegmentGEMMSM90Run function be used for LoRA computing on H20?
#1034 opened Apr 23, 2025 by chenhongyu2048
2
flashinfer.decode.single_decode_with_kv_cache: Floating point exception (core dumped)
#1027 opened Apr 20, 2025 by MenHimChan
[Performance Issue] FlashInfer shows no performance improvement with FP8 compared to BF16 in BatchDecodeWithPagedKVCacheWrapper with page_size=1
#1024 opened Apr 18, 2025 by cscyuge
1
[Bug] FP8 scaling factors (k_scale/v_scale) not taking effect in BatchPrefillWithPagedKVCacheWrapper
#1023 opened Apr 17, 2025 by cscyuge
@yzh119
1
Low performance of POD Attention compared to BatchPrefillWithPagedKVCache
#1022 opened Apr 17, 2025 by Edenzzzz
@yzh119
12
[Feature Request] Llama 4
#1004 opened Apr 6, 2025 by yzh119
3 tasks
1
Does FlashInfer support ViT attention in Qwen2.5_Vl?
#992 opened Apr 1, 2025 by IdeaMeshDyx
[Feature Tracking] MLA-FP8 Hopper kernel
#990 opened Mar 31, 2025 by yzh119
C++ API Stability
#988 opened Mar 30, 2025 by AgrawalAmey
2
Unclear behavior of top_k for k < 1
#979 opened Mar 28, 2025 by sharvil
2
top_k_top_p_sampling_from_logits incompatible with torch.compile + CUDAGraph
#978 opened Mar 28, 2025 by sharvil
6
ProTip! Type g i on any issue or pull request to go back to the issue listing page.