This website requires JavaScript.
Explore
Help
Register
Sign In
helexa
/
cortex
Watch
1
Star
0
Fork
0
You've already forked cortex
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
All Workflows
build-prerelease.yml
ci.yml
Actor
All actors
grenade
Status
All status
Success
Failure
Waiting
Running
fix(gateway): full observability + stop leaking upstream bodies
#161
:
Commit
aa88d37509
pushed by
grenade
main
2026-05-22 04:22:28 +00:00
4m51s
View workflow file
fix(router,handlers): strip trailing slash from rewritten URL + log upstream failures
#159
:
Commit
0f00f72b47
pushed by
grenade
main
2026-05-22 04:15:43 +00:00
4m51s
View workflow file
fix(router): rewrite loopback inference URLs to use neuron's host
#157
:
Commit
9b0ed0b57f
pushed by
grenade
main
2026-05-22 03:45:52 +00:00
12m1s
View workflow file
fix(rpm): migrate legacy helexa-cortex firewalld service to `cortex`
#155
:
Commit
dc2a803266
pushed by
grenade
main
2026-05-22 03:17:53 +00:00
4m45s
View workflow file
feat(stage-8e-3): quantize lm_head in TP Qwen3-Next
#153
:
Commit
e71181499e
pushed by
grenade
main
2026-05-21 20:29:18 +00:00
9m18s
View workflow file
fix(stage-8e-2e): bump quant prefill threshold to M > 64
#151
:
Commit
ee663e5e99
pushed by
grenade
main
2026-05-21 18:53:21 +00:00
2m23s
View workflow file
feat(stage-8e-2d): route quantized matmul by M (prefill vs decode)
#149
:
Commit
34f9b77d9d
pushed by
grenade
main
2026-05-21 18:20:51 +00:00
5m4s
View workflow file
fix(stage-8e-2c): cast bf16/f16 activations to f32 around QMatMul
#147
:
Commit
f084aaab8e
pushed by
grenade
main
2026-05-21 17:10:04 +00:00
4m35s
View workflow file
fix(stage-8e-2b): allow quant on the TP load path
#145
:
Commit
68a606a79c
pushed by
grenade
main
2026-05-21 16:22:05 +00:00
4m40s
View workflow file
feat(stage-8e-2): plumb quant config from ModelSpec to TP load path
#143
:
Commit
4aa71902d0
pushed by
grenade
main
2026-05-21 15:09:27 +00:00
5m36s
View workflow file
feat(stage-8e-1): MaybeQuantLinear primitive + parallel-linear quant variants
#141
:
Commit
bef159b21c
pushed by
grenade
main
2026-05-21 15:03:43 +00:00
6m16s
View workflow file
feat(stage-8d-7): direct safetensors fused-region loader
#139
:
Commit
8d7b099b36
pushed by
grenade
main
2026-05-21 14:54:35 +00:00
4m45s
View workflow file
diag(stage-8d-6): per-layer VRAM logging in TP load path
#137
:
Commit
89d98d1fb2
pushed by
grenade
main
2026-05-21 09:59:25 +00:00
5m10s
View workflow file
feat(stage-8d-5b): wire fused_gdn_gating CUDA kernel
#135
:
Commit
cc95fe28d9
pushed by
grenade
main
2026-05-21 09:18:16 +00:00
10m44s
View workflow file
feat(stage-8d-4): dispatch chunked_gated_delta_rule_recurrence at prefill
#133
:
Commit
09c945f81e
pushed by
grenade
main
2026-05-21 08:52:44 +00:00
1m38s
View workflow file
feat(stage-8d-3): wire causal_conv1d_update/full CUDA kernels
#131
:
Commit
05dc0bad18
pushed by
grenade
main
2026-05-21 08:50:37 +00:00
45s
View workflow file
feat(stage-8d-5): wire gated_delta_rule_recurrence kernel into tp_qwen3_5
#129
:
Commit
10c151efa5
pushed by
grenade
main
2026-05-21 08:49:15 +00:00
4m51s
View workflow file
feat(stage-8d-2): wire gated_delta_rule_recurrence kernel into qwen3_5
#127
:
Commit
44ae927e38
pushed by
grenade
main
2026-05-21 08:42:34 +00:00
2m17s
View workflow file
feat(stage-8d-1): import mistralrs GDN CUDA kernels — build infra only
#125
:
Commit
1ebbe87651
pushed by
grenade
main
2026-05-21 08:39:37 +00:00
4m28s
View workflow file
feat(tp): cancellation-safe inference + structured tracing
#123
:
Commit
70eb6af42b
pushed by
grenade
main
2026-05-21 05:27:36 +00:00
5m27s
View workflow file
fix(tp): always drain worker responses on leader failure
#121
:
Commit
d1a4aad91d
pushed by
grenade
main
2026-05-21 04:45:12 +00:00
5m17s
View workflow file
feat(stage-8c): TP-aware Qwen3-Next (tp_qwen3_5)
#119
:
Commit
95dc8745eb
pushed by
grenade
main
2026-05-20 19:07:53 +00:00
5m0s
View workflow file
fix(qwen3_5): promote beta to F32 alongside q/k/v in delta rule
#117
:
Commit
495d3f7c05
pushed by
grenade
main
2026-05-20 18:18:32 +00:00
4m59s
View workflow file
fix(qwen3_5): tensor names are under `model.language_model.*`, not `model.*`
#115
:
Commit
5c4c8e0eba
pushed by
grenade
main
2026-05-20 13:54:14 +00:00
5m44s
View workflow file
fix(qwen3_5): tensor names are under `model.language_model.*`, not `model.*`
#113
:
Commit
a77f19686e
pushed by
grenade
main
2026-05-20 13:48:22 +00:00
18s
View workflow file
fix(qwen3_5): nested rope_parameters + partial_rotary_factor=0.25
#111
:
Commit
07c44d5db1
pushed by
grenade
main
2026-05-20 13:23:53 +00:00
4m50s
View workflow file
feat(stage-8c): full-attention layer + decoder + Model + ForCausalLM for qwen3_5
#109
:
Commit
e7eb3dab6a
pushed by
grenade
main
2026-05-20 12:57:56 +00:00
5m8s
View workflow file
feat(stage-8c): linear-attention layer (Qwen3-Next GatedDeltaNet)
#107
:
Commit
180274548d
pushed by
grenade
main
2026-05-20 06:35:13 +00:00
5m10s
View workflow file
feat(stage-8c): scaffold qwen3_5 (Qwen3.6) — dispatch + stubs + TP gate
#105
:
Commit
a70f317729
pushed by
grenade
main
2026-05-20 06:03:19 +00:00
5m8s
View workflow file
feat(stage-8b): Llama + Qwen3 MoE families on the candle harness
#103
:
Commit
c6022aa6b9
pushed by
grenade
main
2026-05-20 05:42:19 +00:00
5m47s
View workflow file
First
Previous
1
2
3
4
Next
Last