• Joined on 2026-02-17
grenade pushed to fix/followers-stream-from-the-transfer at grenade/rustingface 2026-09-02 11:34:22 +00:00
14f8342cf8 fix(core): followers stream from the transfer instead of waiting it out
grenade created branch fix/followers-stream-from-the-transfer in grenade/rustingface 2026-09-02 11:34:21 +00:00
grenade pushed to main at grenade/rustingface 2026-09-02 11:34:20 +00:00
d1b1cdf3de Merge branch 'fix/bounded-cold-range-does-not-stall'
9b35dfdc09 fix(core): a cold range that stops short of the end no longer stalls
Compare 2 commits »
grenade closed issue grenade/rustingface#4 2026-09-02 11:34:19 +00:00
A cold prefix range delivers its bytes at once, then stalls on the holdback
grenade created branch fix/bounded-cold-range-does-not-stall in grenade/rustingface 2026-09-02 11:24:55 +00:00
grenade pushed to fix/bounded-cold-range-does-not-stall at grenade/rustingface 2026-09-02 11:24:55 +00:00
9b35dfdc09 fix(core): a cold range that stops short of the end no longer stalls
grenade closed issue grenade/rustingface#3 2026-09-02 11:24:54 +00:00
A deploy during a long download kills the service with SIGABRT
grenade pushed to main at grenade/rustingface 2026-09-02 11:24:54 +00:00
a88bbd1ee2 Merge branch 'fix/drain-does-not-wait-on-blob-streams'
b41964fae0 fix(serve): bound the drain so a restart cannot escalate to SIGABRT
Compare 2 commits »
grenade pushed to fix/drain-does-not-wait-on-blob-streams at grenade/rustingface 2026-09-02 11:16:56 +00:00
b41964fae0 fix(serve): bound the drain so a restart cannot escalate to SIGABRT
grenade created branch fix/drain-does-not-wait-on-blob-streams in grenade/rustingface 2026-09-02 11:16:55 +00:00
grenade opened issue grenade/rustingface#4 2026-09-02 11:13:55 +00:00
A cold prefix range delivers its bytes at once, then stalls on the holdback
grenade opened issue grenade/rustingface#3 2026-09-02 11:13:37 +00:00
A deploy during a long download kills the service with SIGABRT
grenade commented on issue grenade/rustingface#2 2026-09-02 11:04:07 +00:00
A request that joins an in-flight fetch waits in silence for the whole transfer

Measured the pinned client before building on the suggestion above, and it does not hold up. Correcting it.

huggingface_hub 0.36 routes file requests through _request_wrapper -> http_backoff…

grenade opened issue grenade/rustingface#2 2026-09-02 11:02:12 +00:00
A request that joins an in-flight fetch waits in silence for the whole transfer
grenade pushed to main at grenade/rustingface 2026-09-02 10:43:45 +00:00
f724d8f256 ci(deploy): a log diagnostic must not fail a deploy that worked
grenade pushed to main at grenade/rustingface 2026-09-02 10:08:48 +00:00
b638862026 Merge branch 'fix/no-total-duration-cap-on-blob-transfers'
5f91032e6f fix(core): a ranged fetch of a cold file left the client in silence
cfa53e14bd fix(data): a hidden 30s body timeout capped every proxied blob
Compare 3 commits »
grenade closed issue grenade/rustingface#1 2026-09-02 10:08:47 +00:00
A total-duration request_timeout makes large-blob fetches fail deterministically in proxy mode
grenade pushed to feat/qwen4-exp-mtp-head at helexa/helexa 2026-09-02 09:43:40 +00:00
2c852c05cb feat(qwen4_exp): the MTP draft head
1862f0ad2d Merge branch 'docs/mtp-wiring-settled' into feat/qwen4-exp-mtp-head
Compare 2 commits »
grenade created branch feat/qwen4-exp-mtp-head in helexa/helexa 2026-09-02 09:43:39 +00:00
grenade commented on issue helexa/helexa#313 2026-09-02 09:34:39 +00:00
qwen4_exp F: use the shipped MTP head as a draft model

Settled against vLLM — and the spec had one of the norms wrong

Cloned vllm-project/vllm (at 76ba321). The head is implemented at vllm/models/qwen4_exp/nvidia/mtp.py. vLLM calls the…