index
:
ffwd
master
Fastforward embedding inference engine
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
Commit message (
Collapse
)
Author
Age
Files
Lines
...
*
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
|
*
server: bound merged batches by token budget
Onur Gündüz
2026-06-24
2
-6
/
+46
|
*
server: fix tokenizer data race under concurrency
Onur Gündüz
2026-06-24
3
-22
/
+8
|
*
server: make tokenize/render overlap adaptive, drop env switches
Onur Gündüz
2026-06-24
4
-146
/
+50
|
*
chore: document server diagnostic env switches
Onur Gündüz
2026-06-24
1
-0
/
+12
|
*
server: tokenize requests off the worker thread
Onur Gündüz
2026-06-24
3
-23
/
+209
|
*
server: render inline when idle, defer only under backlog
Onur Gündüz
2026-06-24
3
-6
/
+35
|
*
server: pack all compatible requests into token-budget batches
Onur Gündüz
2026-06-24
1
-20
/
+46
|
*
server: render embedding responses off worker
Onur Gündüz
2026-06-23
6
-16
/
+238
|
*
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
2
-66
/
+226
|
*
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
5
-170
/
+907
|
*
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
4
-1357
/
+102
|
*
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
2
-4
/
+22
|
*
build: source all.bash checks from tests, drop precision-drift tool
Onur Gündüz
2026-06-21
3
-9
/
+3
|
*
devtools: fix container-build-test.sh (python3 dep, clean-tree abort)
Onur Gündüz
2026-06-21
1
-2
/
+12
|
*
build: add check-sanitize (ASan/UBSan hermetic run) to all.bash
Onur Gündüz
2026-06-21
1
-8
/
+44
|
*
build: -Werror=implicit-function-declaration to catch missing prototypes
Onur Gündüz
2026-06-21
1
-1
/
+5
|
*
tests: make qwen3 parity token-count check best-effort
Onur Gündüz
2026-06-21
1
-6
/
+12
|
*
build: define _DEFAULT_SOURCE so glibc declares strdup under -std=c11
Onur Gündüz
2026-06-21
1
-0
/
+5
|
*
devtools: per-backend binaries in compare_model_embeddings for cpu-vs-cuda
Onur Gündüz
2026-06-21
1
-11
/
+33
|
*
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
|
*
bench: select per-backend binary in bench_matrix
Onur Gündüz
2026-06-21
1
-4
/
+45
|
*
build: fix checks aggregate under bash 3.2 (empty array + set -u)
Onur Gündüz
2026-06-21
1
-5
/
+9
|
*
devtools: analyze bench sources with the tools/server include path
Onur Gündüz
2026-06-21
1
-1
/
+2
|
[prev]
[next]