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
*
docs: update README intro
HEAD
v0.3.0
master
Onur Gündüz
2026-07-14
1
-19
/
+9
*
chore: move the server README to top-level
Onur Gündüz
2026-07-14
2
-271
/
+263
*
chore: update README
Onur Gündüz
2026-07-14
1
-26
/
+0
*
bench: add tokens-per-text and float embeddings to the server bench
Onur Gündüz
2026-07-04
1
-6
/
+24
*
server: bound the collect window by the batch token budget
Onur Gündüz
2026-07-04
2
-0
/
+63
*
server: per-model input token cap, auto-truncate, and 429 admission
Onur Gündüz
2026-07-04
9
-24
/
+203
*
server: make the per-request token cap configurable
Onur Gündüz
2026-07-02
5
-6
/
+20
*
cuda: default cuDNN attention to Qwen only, BERT opt-in
Onur Gündüz
2026-07-02
1
-12
/
+19
*
cuda: add cuDNN fused attention path with runtime fallback
Onur Gündüz
2026-07-02
102
-8
/
+80725
*
docs: update README
Onur Gündüz
2026-06-30
1
-1
/
+2
*
docs: update README
Onur Gündüz
2026-06-30
1
-23
/
+38
*
ci: fix the invalid filename in gh release command
v0.2.0
Onur Gündüz
2026-06-30
1
-1
/
+1
*
ci: add version label to release packages
Onur Gündüz
2026-06-30
1
-1
/
+1
*
ci: do not include README in release packages
Onur Gündüz
2026-06-30
1
-2
/
+2
*
ci: build and publish CUDA release
Onur Gündüz
2026-06-28
1
-0
/
+19
*
ci: add dry run option to workflow
Onur Gündüz
2026-06-28
1
-0
/
+13
*
ci: remove yyjson from apt install list
Onur Gündüz
2026-06-28
1
-2
/
+0
*
docs: fix heading size
Onur Gündüz
2026-06-28
1
-1
/
+1
*
docs: update README
Onur Gündüz
2026-06-28
1
-13
/
+29
*
docs: update server README to clarify GPU precision flags
Onur Gündüz
2026-06-27
1
-17
/
+40
*
chore: update README.md
Onur Gündüz
2026-06-27
1
-11
/
+16
*
chore: update project name in LICENSE
Onur Gündüz
2026-06-27
1
-1
/
+1
*
server: add README.md
Onur Gündüz
2026-06-27
1
-0
/
+219
*
gitignore: add bench folders to ignore list
Onur Gündüz
2026-06-27
1
-0
/
+4
*
chore: clean up comment formatting and wording
Onur Gündüz
2026-06-27
96
-746
/
+792
*
cuda: skip Qwen flash softmax rescale when running max is stable
Onur Gündüz
2026-06-26
1
-8
/
+33
*
cuda: load Qwen flash V with ldmatrix.trans instead of gather
Onur Gündüz
2026-06-26
1
-35
/
+83
*
build: vendor yyjson 0.12.0 in deps/yyjson
Onur Gündüz
2026-06-25
10
-17
/
+19361
*
cuda: skip O(L^2) score buffer for qwen flash path (enables 32k)
Onur Gündüz
2026-06-25
1
-1
/
+7
*
cuda: stage compact GQA K/V in qwen attention, halve the expand
Onur Gündüz
2026-06-25
1
-14
/
+47
*
chore: fix permissions for test scripts and devtools
Onur Gündüz
2026-06-25
9
-0
/
+0
*
chore: run clang-format
Onur Gündüz
2026-06-25
20
-432
/
+380
*
build: update build info and accelerator labels
Onur Gündüz
2026-06-25
5
-34
/
+30
*
server: store the Server-Timing header inline in the job
Onur Gündüz
2026-06-25
2
-10
/
+11
*
server: encode base64 embeddings directly into the response buffer
Onur Gündüz
2026-06-25
5
-67
/
+97
*
server: drop the throwaway buffer in the base64 float path
Onur Gündüz
2026-06-25
1
-8
/
+4
*
server: remove the dead auth field
Onur Gündüz
2026-06-25
2
-2
/
+0
*
server: move the request body instead of copying it
Onur Gündüz
2026-06-25
1
-2
/
+3
*
chore: update README
Onur Gündüz
2026-06-25
1
-13
/
+20
*
all: migrate to yyjson
Onur Gündüz
2026-06-25
19
-323
/
+354
*
cuda: skip per-warp future key tiles in causal qwen attention
Onur Gündüz
2026-06-25
1
-65
/
+95
*
cuda: double-buffer qwen flash K/V staging with cp.async
Onur Gündüz
2026-06-24
1
-82
/
+228
*
cuda: prefetch bert flash QK ahead of softmax to overlap the tensor cores
Onur Gündüz
2026-06-24
1
-50
/
+99
*
cuda: read bert flash K directly, drop the shared-memory transpose
Onur Gündüz
2026-06-24
1
-40
/
+65
*
cuda: broaden bert flash kv pipeline to all flash batches
Onur Gündüz
2026-06-24
1
-8
/
+10
*
tokenizer: parse BPE vocab.json with yyjson
Onur Gündüz
2026-06-24
1
-127
/
+25
*
api: parse model config with yyjson instead of a substring scanner
Onur Gündüz
2026-06-24
1
-77
/
+94
*
build: vendor yyjson 0.12.0 as the core JSON library
Onur Gündüz
2026-06-24
2
-0
/
+6
*
tests: cover CUDA reduced-precision stack and add determinism gate
Onur Gündüz
2026-06-24
1
-25
/
+45
*
cuda: fix bert reduced-precision ffn gate-up output aliasing its input
Onur Gündüz
2026-06-24
1
-129
/
+156
[next]