Skip to content

Actions: EricLBuehler/mistral.rs

docs

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
1,262 workflow runs
1,262 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Handle CUDA_NVCC_FLAGS in flash attn v3
docs #1262: Commit e2f9648 pushed by EricLBuehler
February 25, 2025 03:07 7m 56s master
February 25, 2025 03:07 7m 56s
Handle CUDA_NVCC_FLAGS in flash attn v3 (#1160)
docs #1261: Commit 153a093 pushed by EricLBuehler
February 25, 2025 02:57 8m 34s master
February 25, 2025 02:57 8m 34s
Ensure we do not bind the port for daemon processes (#1158)
docs #1260: Commit 6b9cb1f pushed by EricLBuehler
February 24, 2025 22:30 7m 42s master
February 24, 2025 22:30 7m 42s
Fix non-cuda
docs #1259: Commit f83d843 pushed by EricLBuehler
February 24, 2025 04:02 7m 49s master
February 24, 2025 04:02 7m 49s
Remove .gitmodules
docs #1258: Commit cbc5075 pushed by EricLBuehler
February 23, 2025 03:39 7m 43s master
February 23, 2025 03:39 7m 43s
Multiple processes for TP (#1152)
docs #1257: Commit eadc1eb pushed by EricLBuehler
February 23, 2025 01:27 7m 55s master
February 23, 2025 01:27 7m 55s
Fix chat sampling response (#1154)
docs #1256: Commit 8d89c14 pushed by EricLBuehler
February 19, 2025 17:02 7m 52s master
February 19, 2025 17:02 7m 52s
Fix non-cuda
docs #1255: Commit 71650a4 pushed by EricLBuehler
February 16, 2025 21:11 8m 13s master
February 16, 2025 21:11 8m 13s
Blockwise FP8 CUDA fix for cc < 800 (#1150)
docs #1254: Commit 9ec86d8 pushed by EricLBuehler
February 16, 2025 19:59 8m 3s master
February 16, 2025 19:59 8m 3s
FP8 blockwise dequant CUDA kernel (#1149)
docs #1253: Commit 1b8c077 pushed by EricLBuehler
February 16, 2025 19:44 7m 59s master
February 16, 2025 19:44 7m 59s
February 16, 2025 18:24 7m 45s
February 16, 2025 04:55 8m 3s
Patch check for multi-node at the same time as pipeline parallel
docs #1250: Commit 098776f pushed by EricLBuehler
February 16, 2025 03:59 7m 57s master
February 16, 2025 03:59 7m 57s
Handle HF_HUB_CACHE env var (#1146)
docs #1249: Commit 6a92f70 pushed by EricLBuehler
February 16, 2025 03:29 7m 52s master
February 16, 2025 03:29 7m 52s
Use cudarc 0.13.5 - CUDA 12.8 support (#1145)
docs #1248: Commit 2e66544 pushed by EricLBuehler
February 16, 2025 03:07 11m 32s master
February 16, 2025 03:07 11m 32s
Integrate fused MLP mul-act for more models! (#1144)
docs #1247: Commit e2830b5 pushed by EricLBuehler
February 16, 2025 03:03 7m 44s master
February 16, 2025 03:03 7m 44s
Short-circuit dry sampling (#1143)
docs #1246: Commit 9f4fbd2 pushed by EricLBuehler
February 15, 2025 22:34 7m 48s master
February 15, 2025 22:34 7m 48s
Fuse MLP mul-and-act (#1142)
docs #1245: Commit c65d8f6 pushed by EricLBuehler
February 15, 2025 03:59 8m 49s master
February 15, 2025 03:59 8m 49s
Revamp speculative decoding! (#1027)
docs #1244: Commit dd5aee1 pushed by EricLBuehler
February 15, 2025 03:13 8m 0s master
February 15, 2025 03:13 8m 0s
Remove failing cp command from readme (#1141)
docs #1243: Commit 5e689c9 pushed by EricLBuehler
February 14, 2025 18:00 8m 3s master
February 14, 2025 18:00 8m 3s
Some fixes for Qwen, #1134
docs #1242: Commit 87a7c23 pushed by EricLBuehler
February 13, 2025 22:33 8m 13s master
February 13, 2025 22:33 8m 13s
FIx for llama multi node (#1136)
docs #1241: Commit c9ac321 pushed by EricLBuehler
February 13, 2025 01:25 7m 44s master
February 13, 2025 01:25 7m 44s
Add jinja strftime_now function (#1132)
docs #1240: Commit 323e7cd pushed by EricLBuehler
February 12, 2025 01:37 7m 47s master
February 12, 2025 01:37 7m 47s
Fix mistral 2501 gguf (#1131)
docs #1239: Commit 8dff440 pushed by EricLBuehler
February 12, 2025 00:44 8m 3s master
February 12, 2025 00:44 8m 3s
Add an NCCL feature flag (#1129)
docs #1238: Commit bd5532c pushed by EricLBuehler
February 11, 2025 23:23 8m 13s master
February 11, 2025 23:23 8m 13s