index
:
ffwd
master
Fastforward embedding inference engine
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
Commit message (
Expand
)
Author
Age
Files
Lines
*
mlx: prepare contiguous linear weights
Onur Gündüz
2026-06-14
1
-4
/
+21
*
mlx: optimize ragged embedding batches
Onur Gündüz
2026-06-14
1
-2
/
+114
*
build: add address/undefined sanitizers to debug builds
Onur Gündüz
2026-06-14
1
-2
/
+4
*
chore: address static analyzer warnings
Onur Gündüz
2026-06-14
5
-27
/
+92
*
kernels: parallelize large rmsnorm rows
Onur Gündüz
2026-06-14
1
-5
/
+48
*
mlx: use prefix pooling for f32 contextual spans
Onur Gündüz
2026-06-14
1
-32
/
+138
*
mlx: cache transposed linear weights
Onur Gündüz
2026-06-14
1
-4
/
+46
*
server: expose worker stage timing
Onur Gündüz
2026-06-14
1
-13
/
+95
*
tokenizer: add reusable encode workspace
Onur Gündüz
2026-06-14
4
-2
/
+478
*
mlx: keep late maxsim device resident
Onur Gündüz
2026-06-14
2
-25
/
+405
*
late: add packed maxsim scoring
Onur Gündüz
2026-06-14
4
-7
/
+45
*
late: add mlx token vector support
Onur Gündüz
2026-06-14
2
-8
/
+235
*
late: add CPU token vectors and maxsim
Onur Gündüz
2026-06-14
2
-5
/
+223
*
all: add validation for late-interaction model compat
Onur Gündüz
2026-06-14
2
-1
/
+48
*
kernels: vectorize bf16 widening on arm
Onur Gündüz
2026-06-14
1
-0
/
+14
*
kernels: use sgemv for single-row f32 linear
Onur Gündüz
2026-06-14
2
-4
/
+11
*
kernels: add neon rope apply path
Onur Gündüz
2026-06-14
1
-0
/
+21
*
build: add tmp to .gitignore
Onur Gündüz
2026-06-14
1
-0
/
+1
*
dist: add fp16 activation transport
Onur Gündüz
2026-06-14
3
-23
/
+191
*
server: support http keep-alive
Onur Gündüz
2026-06-14
1
-11
/
+98
*
mlx: add opt-in 8-bit weight quantization
Onur Gündüz
2026-06-14
7
-33
/
+332
*
cpu: reuse tiled attention scratch buffers
Onur Gündüz
2026-06-14
3
-15
/
+77
*
mlx: harden model and buffer validation
Onur Gündüz
2026-06-14
1
-46
/
+156
*
server: bound mlx batches by padded token rows
Onur Gündüz
2026-06-14
1
-2
/
+25
*
mlx: simplify equal-length embedding pooling
Onur Gündüz
2026-06-14
1
-24
/
+35
*
mlx: pool contextual bf16 spans before widening
Onur Gündüz
2026-06-14
1
-11
/
+9
*
server: reject unsafe mlx model overcommit
Onur Gündüz
2026-06-14
5
-0
/
+129
*
server: simplify context separator logic
Onur Gündüz
2026-06-14
2
-13
/
+5
*
server: batch contextual document inference
Onur Gündüz
2026-06-14
5
-226
/
+567
*
mlx: pool contextual spans on device
Onur Gündüz
2026-06-14
1
-17
/
+95
*
cpu: tile packed attention through blas
Onur Gündüz
2026-06-14
1
-54
/
+110
*
server: batch standard requests by token budget
Onur Gündüz
2026-06-14
3
-11
/
+77
*
dist: add direct two-node fp32 inference
Onur Gündüz
2026-06-14
4
-19
/
+874
*
dist: load distributed layer shards selectively
Onur Gündüz
2026-06-14
4
-29
/
+122
*
build: add client directory to .gitignore
Onur Gündüz
2026-06-14
1
-0
/
+1
*
dist: add distributed layer-slice foundation
Onur Gündüz
2026-06-14
4
-228
/
+412
*
api: add opt-in l2 normalization helper
Onur Gündüz
2026-06-14
2
-3
/
+40
*
server: align embedding quantization with perplexity
Onur Gündüz
2026-06-14
4
-51
/
+28
*
server: support float embedding responses
Onur Gündüz
2026-06-14
1
-18
/
+52
*
server: add embeddings micro-batching
Onur Gündüz
2026-06-14
3
-100
/
+358
*
server: implement HTTP API with libae integration
Onur Gündüz
2026-06-14
22
-27
/
+4715
*
build: add plx_server to .gitignore
Onur Gündüz
2026-06-14
1
-0
/
+1
*
cpu: keep batch offsets in workspace
Onur Gündüz
2026-06-14
1
-10
/
+38
*
cpu: tighten workspace growth
Onur Gündüz
2026-06-14
1
-4
/
+14
*
cpu: reduce initial workspace capacity
Onur Gündüz
2026-06-14
1
-1
/
+2
*
server: report workspace memory
Onur Gündüz
2026-06-14
3
-3
/
+77
*
kernels,cpu: fuse tiny BF16 gate up projections
Onur Gündüz
2026-06-14
3
-3
/
+126
*
kernels,cpu: fuse small BF16 QKV projections
Onur Gündüz
2026-06-14
3
-20
/
+67
*
cpu: reuse MLP scratch buffer
Onur Gündüz
2026-06-14
1
-6
/
+3
*
tokenizer: reduce merge allocation
Onur Gündüz
2026-06-14
1
-10
/
+41
[next]