issues
search
flexflow
/
FlexFlow
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
https://flexflow.readthedocs.io
Apache License 2.0
1.58k
stars
218
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Implementations for methods for machine_views and associated modules
#1429
Marsella8
opened
10 hours ago
1
modify constructor and allocate weights
#1428
goliaro
opened
1 day ago
0
manually creating cg and pcg for models
#1427
Bob-Chen222
opened
5 days ago
1
Graph testing
#1426
Marsella8
opened
6 days ago
2
Request for Graph Pruning Algorithm Code Location in FlexLLM
#1425
zbtrs
opened
1 week ago
0
Run `proj dtgen` in CI
#1424
lockshaw
closed
6 days ago
1
Sp-ization Algorithm
#1423
Marsella8
opened
1 week ago
1
Fix input, weight, noop in local execution
#1422
reyna-abhyankar
opened
1 week ago
0
Fix `cudnnSetTensorDescriptorFromArrayShape`
#1421
reyna-abhyankar
opened
1 week ago
0
Rename `real_type` to `real_type_t`
#1420
lockshaw
opened
1 week ago
0
Convert allocator to arena
#1419
reyna-abhyankar
opened
1 week ago
0
Local execution tests
#1418
reyna-abhyankar
opened
1 week ago
2
Fix calls for softmax_kernels init_kernel
#1417
oOTigger
opened
2 weeks ago
0
Change `Allocator` ownership model
#1416
reyna-abhyankar
opened
2 weeks ago
0
Local Backing: Gradient Tensor Allocation
#1415
reyna-abhyankar
opened
2 weeks ago
0
Analytical function for estimating communication cost
#1414
reyna-abhyankar
opened
2 weeks ago
0
SLO-aware specscheduler
#1413
Flechman
opened
2 weeks ago
0
partial fix on substitution and peg
#1412
Bob-Chen222
closed
6 days ago
1
Add `ParallelComputationGraphBuilder`
#1411
lockshaw
closed
2 weeks ago
3
Local Cost Estimator
#1410
reyna-abhyankar
closed
1 week ago
3
Change datatype for linear kernels away from void * in .cc
#1409
oOTigger
closed
3 weeks ago
0
Refactor `element_unary_kernels.cpp`
#1408
reyna-abhyankar
opened
3 weeks ago
0
Hip support(draft)
#1407
Bob-Chen222
opened
4 weeks ago
0
filtering out dtgen related files in code coverage report
#1406
Bob-Chen222
closed
4 weeks ago
1
Implement `is_valid` (or remove it) in parallel shape inference
#1405
lockshaw
opened
1 month ago
0
refactor for softmax, split, topk, transpose
#1404
Bob-Chen222
closed
4 weeks ago
1
hip refactor for reduce, reduction, replicate, reshape and reverse
#1403
Bob-Chen222
closed
3 weeks ago
1
Hip refactor for attention, batch, combine, cast, conv
#1402
Bob-Chen222
closed
3 weeks ago
1
Code coverage
#1401
Bob-Chen222
closed
1 month ago
0
Local backing
#1400
reyna-abhyankar
closed
3 weeks ago
1
Update CUDA toolchain version
#1399
oOTigger
closed
3 weeks ago
0
Add local logging
#1398
reyna-abhyankar
opened
1 month ago
0
Change datatype for linear kernels away from `void *` in `.cc`
#1397
reyna-abhyankar
opened
1 month ago
0
Code Coverage Support
#1396
Bob-Chen222
closed
1 month ago
0
SampleIdxs creates large futures
#1395
suranap
opened
1 month ago
0
PCG serialization, rapidcheck, dtgen, and shape inference
#1394
lockshaw
closed
4 weeks ago
1
Add profiling and write statistics to output file
#1393
Flechman
closed
1 month ago
0
Some question about the Flexflow and example/cpp/moe
#1392
yjsunn
opened
1 month ago
4
Graph Documentation
#1391
Marsella8
closed
1 month ago
1
Optional CodeCoverage Building Instrumentation
#1390
Bob-Chen222
closed
1 month ago
3
Local Execution: Op refactor
#1389
reyna-abhyankar
closed
1 month ago
1
Computation Graph and Builder
#1388
reyna-abhyankar
closed
1 month ago
0
Local Execution: Op Refactor
#1387
reyna-abhyankar
closed
1 month ago
0
Local allocator
#1386
reyna-abhyankar
closed
1 month ago
0
Difference of peft branch
#1385
czq693497091
closed
4 weeks ago
1
Add unit tests for subset of kernels
#1384
oOTigger
opened
1 month ago
5
Documentation for graph library
#1383
Marsella8
closed
6 days ago
1
Fix rapidcheck
#1382
yingyee0111
closed
2 months ago
0
Applying Lora Layers to Attention Operators
#1381
april-yyt
closed
1 month ago
0
Code Coverage Support
#1380
Bob-Chen222
closed
1 month ago
2
Next