index
:
ffwd
master
Fastforward embedding inference engine
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
libffwd
(
follow
)
Commit message (
Collapse
)
Author
Age
Files
Lines
*
chore: clean up comment formatting and wording
Onur Gündüz
2026-06-27
42
-452
/
+439
|
*
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
1
-0
/
+6
|
*
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: run clang-format
Onur Gündüz
2026-06-25
14
-392
/
+345
|
*
build: update build info and accelerator labels
Onur Gündüz
2026-06-25
3
-28
/
+24
|
*
all: migrate to yyjson
Onur Gündüz
2026-06-25
3
-6
/
+3
|
*
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
1
-0
/
+3
|
*
cuda: fix bert reduced-precision ffn gate-up output aliasing its input
Onur Gündüz
2026-06-24
1
-129
/
+156
|
*
cuda: pipeline bert flash kv staging
Onur Gündüz
2026-06-24
1
-179
/
+649
|
*
cuda: widen bert flash key tile to 64, hoist q fragments
Onur Gündüz
2026-06-24
1
-100
/
+146
|
*
cuda: trim bert reduced scratch
Onur Gündüz
2026-06-24
1
-73
/
+213
|
*
cuda: stage bert flash kv directly from qkv16
Onur Gündüz
2026-06-23
1
-73
/
+143
|
*
cuda: store bert qkv in 16-bit for flash batches
Onur Gündüz
2026-06-23
1
-40
/
+120
|
*
cuda: fuse bert qkv bias via cublaslt epilogue (f32 output)
Onur Gündüz
2026-06-23
1
-40
/
+59
|
*
cuda: cache the cublaslt gate-up matmul plan per shape
Onur Gündüz
2026-06-23
1
-77
/
+114
|
*
cuda: fuse bert gate-up bias+gelu via cublaslt epilogue
Onur Gündüz
2026-06-23
1
-65
/
+225
|
*
cuda: write bert residual delta 16-bit on the residual16 path
Onur Gündüz
2026-06-23
1
-10
/
+155
|
*
chore: clang-format libffwd/cuda.cu
Onur Gündüz
2026-06-23
1
-93
/
+92
|
*
cuda: add bert ffn16 intermediate path
Onur Gündüz
2026-06-23
3
-168
/
+905
|
*
cuda: auto-enable bert residual16 for long batches
Onur Gündüz
2026-06-23
1
-8
/
+12
|
*
cuda: gate bert bf16 residual stream
Onur Gündüz
2026-06-23
1
-33
/
+172
|
*
cuda: store weight dtype per context
Onur Gündüz
2026-06-22
2
-48
/
+58
|
*
cuda: prune attention experiments
Onur Gündüz
2026-06-22
1
-1330
/
+17
|
*
cuda: add opt-in BERT flash attention for head_dim 32
Onur Gündüz
2026-06-22
1
-49
/
+66
|
*
cuda: make bf16 BERT flash attention the default on the head_dim-64 path
Onur Gündüz
2026-06-22
1
-6
/
+9
|
*
cuda: add gated bf16 flash attention for the BERT shape (head_dim 64)
Onur Gündüz
2026-06-22
1
-6
/
+237
|
*
cuda: auto-enable bf16-activation BERT path above a token-count gate
Onur Gündüz
2026-06-22
1
-9
/
+18
|
*
cuda: add gated bf16-activation BERT path
Onur Gündüz
2026-06-22
1
-48
/
+142
|
*
cuda: prepack streaming K as bf16
Onur Gündüz
2026-06-22
1
-44
/
+65
|
*
cuda: promote tc3 to the default Qwen bf16 attention path
Onur Gündüz
2026-06-22
1
-16
/
+32
|
*
cuda: add qwen tc3 ldmatrix attention
Onur Gündüz
2026-06-22
1
-8
/
+460
|
*
cuda: add K/V-sharing bf16 tensor-core attention (tc2)
Onur Gündüz
2026-06-22
1
-30
/
+227
|
*
cuda: add qwen bf16 tensor-core flash attention
Onur Gündüz
2026-06-22
1
-4
/
+459
|
*
cuda: add register-resident streaming attention behind the flag
Onur Gündüz
2026-06-22
1
-4
/
+172
|
*
cuda: BERT bf16-compute GEMMs skip the f32 weight widen
Onur Gündüz
2026-06-21
1
-6
/
+14
|
*
cuda: add gated streaming attention prototype
Onur Gündüz
2026-06-21
1
-0
/
+383
|
*
cuda: fuse BERT elementwise kernels
Onur Gündüz
2026-06-21
1
-73
/
+96
|
*
cuda: fix bf16 BERT batched-attention buffer-layout mismatch
Onur Gündüz
2026-06-21
1
-4
/
+16
|
*
cuda: restore embed_tokens member name (build fix)
Onur Gündüz
2026-06-21
1
-6
/
+6
|
*
chore: clang-format cuda.cu
Onur Gündüz
2026-06-21
1
-39
/
+34
|
[next]