issues
search
flashinfer-ai
/
flashinfer
FlashInfer: Kernel Library for LLM Serving
https://flashinfer.ai
Apache License 2.0
1.14k
stars
102
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Fix compile/assert on group_size
#247
Qubitium
closed
3 months ago
1
Add group_size 7 and fix compat with Yi 1.5 34b
#246
Qubitium
closed
4 months ago
3
multiple definition of `cuda::__3::pipeline...
#245
jpf888
opened
4 months ago
0
Move -Wno-switch-bool argument to cxx from nvcc
#244
mgerstgrasser
closed
4 months ago
0
Compilation fails due to "-Wno-switch-bool" nvcc flag
#243
mgerstgrasser
closed
4 months ago
0
能否支持Volta/Tesla架构?
#242
alexngng
closed
1 month ago
2
bugfix: Fix dispatcher in src directory
#241
yzh119
closed
4 months ago
0
bugfix: fix the `generate_dispatch_inc` script
#240
yzh119
closed
4 months ago
0
compilation: Suppress switch bool warning
#239
yzh119
closed
4 months ago
0
sampling: expose sampling APIs in pytorch
#238
yzh119
closed
4 months ago
0
Support MLA (Multi-Head Latent Attention) in DeepSeek-v2
#237
yzh119
opened
4 months ago
4
doc: bump documentation version
#236
yzh119
closed
4 months ago
0
cmake: macro trimming
#235
yzh119
closed
4 months ago
0
ci: update release wheel yaml
#234
yzh119
closed
4 months ago
0
fix: remove 8 from default page size
#233
yzh119
closed
4 months ago
0
chore(main): release 0.0.5
#232
github-actions[bot]
closed
2 months ago
1
fix: fix macro to suppress compilation warning
#231
yzh119
closed
4 months ago
0
Revert "ci: remove multi-threading in nvcc compile flags (#229)"
#230
yzh119
closed
4 months ago
0
ci: remove multi-threading in nvcc compile flags
#229
yzh119
closed
4 months ago
0
bugfix: fix MANIFEST.in
#228
yzh119
closed
4 months ago
0
Support torch 2.3
#227
rkooo567
closed
4 months ago
3
bugfix: fix the potential issue of sampling kernels
#226
yzh119
closed
4 months ago
0
bugfix: Fix the correctness issue of sampling kernel
#225
yzh119
closed
4 months ago
0
Fix implicit cast in sampling
#224
abcdabcd987
closed
4 months ago
0
support versatile gqa size for batch prefill
#223
xuzhenqi
closed
4 months ago
3
TypeError: get_cu_file_str() missing 1 required positional argument: 'idtype'
#222
xuzhenqi
closed
4 months ago
1
bugfix: fix sampler's implementation bug when dtype is not float32
#221
yzh119
closed
4 months ago
0
cmake: fix cmake files
#220
yzh119
closed
4 months ago
0
misc: make max_top_p/k_rounds a input argument instead of template parameter
#219
yzh119
closed
4 months ago
0
fix: revert #144
#218
yzh119
closed
4 months ago
1
[BugFix] Fix build error related to dispatch page size
#217
esmeetu
closed
4 months ago
1
ci: add pytorch 2.3 to matrix
#216
yzh119
closed
4 months ago
0
[TVMWrapper] Add wrapper functions for sampler
#215
MasterJH5574
closed
4 months ago
0
misc: parallel sampling from probability
#214
yzh119
closed
4 months ago
0
sampling: support parallel top-p sampling
#213
yzh119
closed
4 months ago
0
perm: optimize sampling performance
#212
yzh119
closed
4 months ago
0
sampling: fix alignment issue for vocab_size not divisible by vec_size
#211
yzh119
closed
4 months ago
0
dependency: update submodules
#210
yzh119
closed
4 months ago
0
move dispatch for batch prefill
#209
abcdabcd987
closed
4 months ago
0
bench: add sampling & norm benchmarks
#208
yzh119
closed
4 months ago
0
misc: fused kernel for sampling and normalization functions
#207
yzh119
closed
4 months ago
0
[CMAKE] Make generation option configuration
#205
tqchen
closed
5 months ago
0
Fixes a misformated macros
#204
sighingnow
closed
5 months ago
0
Update CMakeLists.txt
#203
shreygupta2809
closed
5 months ago
0
Vllm support
#202
MikeChenfu
closed
1 week ago
1
Enable GQA group size = 6
#201
vinx13
closed
5 months ago
1
feat:support any num_heads for get_alibi_slope
#200
yz-tang
closed
5 months ago
0
[LoRA] Roadmap of LoRA operators
#199
yzh119
opened
5 months ago
1
[CMake] Add positional independent code (PIC) option to kernels
#198
MasterJH5574
closed
5 months ago
3
remove duplicates of _get_cache_buf func
#197
HSQ79815
closed
5 months ago
0
Previous
Next